Une comparaison d’estimateurs non paramétriques pour les fonctions de répartition de populations finies
5. Étude en simulationUne comparaison d’estimateurs non paramétriques pour les fonctions de répartition de populations finies
5. Étude en simulation
À la présente section, nous analysons
certains résultats de simulation. Notre objectif est de comparer l’efficacité
par rapport au plan de sondage des estimateurs des fonctions de répartition
présentés à la section 2 et des estimateurs de la variance présentés à la
section 4. Les résultats des simulations s’appliquent à l’échantillonnage
aléatoire simple sans remise et à l’échantillonnage de Poisson avec
probabilités d’inclusion inégales. À titre de référence, nous avons également
inclus dans l’étude en simulation l’estimateur de la fonction de répartition de
Horvitz-Thompson
F
^
π
(
t
)
:
=
1
N
∑
j
∈
s
π
j
−
1
I
(
y
j
≤
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaaceWGgbGbaK
aadaWgaaWcbaGaeqiWdahabeaakmaabmaabaGaamiDaaGaayjkaiaa
wMcaaiaaiQdacaaI9aWaaSaaaeaacaaIXaaabaGaamOtaaaadaaeqb
qaaiabec8aWnaaDaaaleaacaWGQbaabaGaeyOeI0IaaGymaaaakiaa
dMeadaqadaqaaiaadMhadaWgaaWcbaGaamOAaaqabaGccqGHKjYOca
WG0baacaGLOaGaayzkaaaaleaacaWGQbGaeyicI4Saam4Caaqab0Ga
eyyeIuoaaaa@51AA@
et l’estimateur de variance
correspondant
V
˜
(
F
^
π
(
t
)
)
:=
1
N
2
∑
i
,
j
∈
s
π
i
,
j
−
π
i
π
j
π
i
,
j
π
i
π
j
I
(
y
i
≤
t
)
I
(
y
j
≤
t
)
.
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaaceWGwbGbaG
aadaqadaqaaiqadAeagaqcamaaBaaaleaacqaHapaCaeqaaOWaaeWa
aeaacaWG0baacaGLOaGaayzkaaaacaGLOaGaayzkaaGaaGOoaiaai2
dadaWcaaqaaiaaigdaaeaacaWGobWaaWbaaSqabeaacaaIYaaaaaaa
kmaaqafabeWcbaGaamyAaiaaiYcacaWGQbGaeyicI4Saam4Caaqab0
GaeyyeIuoakmaalaaabaGaeqiWda3aaSbaaSqaaiaadMgacaaISaGa
amOAaaqabaGccqGHsislcqaHapaCdaWgaaWcbaGaamyAaaqabaGccq
aHapaCdaWgaaWcbaGaamOAaaqabaaakeaacqaHapaCdaWgaaWcbaGa
amyAaiaaiYcacaWGQbaabeaakiabec8aWnaaBaaaleaacaWGPbaabe
aakiabec8aWnaaBaaaleaacaWGQbaabeaaaaGccaWGjbWaaeWaaeaa
caWG5bWaaSbaaSqaaiaadMgaaeqaaOGaeyizImQaamiDaaGaayjkai
aawMcaaiaadMeadaqadaqaaiaadMhadaWgaaWcbaGaamOAaaqabaGc
cqGHKjYOcaWG0baacaGLOaGaayzkaaGaaiOlaaaa@6F9C@
Nous avons considéré des
populations artificielles ainsi que réelles. Les premières ont été obtenues en
générant
N
=
1
000
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWGobGaey
ypa0JaaGymaiaaysW7caaIWaGaaGimaiaaicdaaaa@3E40@
valeurs
x
i
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWG4bWaaS
baaSqaaiaadMgaaeqaaaaa@3A08@
à partir de variables
aléatoires i.i.d. de loi uniforme avec
support sur l’intervalle
(
0
,
1
)
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaadaqadaqaai
aaicdacaGGSaGaaGymaaGaayjkaiaawMcaaaaa@3B9F@
et en les combinant avec
trois types de fonction de régression
m
(
x
)
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWGTbWaae
WaaeaacaWG4baacaGLOaGaayzkaaaaaa@3B69@
et deux types de composantes
de l’erreur
ε
i
.
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacqaH1oqzda
WgaaWcbaGaamyAaaqabaGccaGGUaaaaa@3B6E@
Les fonctions de régression
sont i)
m
(
x
)
=
0
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWGTbWaae
WaaeaacaWG4baacaGLOaGaayzkaaGaeyypa0JaaGimaaaa@3D29@
(uniforme), ii)
m
(
x
)
=
10
x
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWGTbWaae
WaaeaacaWG4baacaGLOaGaayzkaaGaeyypa0JaaGymaiaaicdacaWG
4baaaa@3EE1@
(linéaire) et iii)
m
(
x
)
=
10
x
1
/
4
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWGTbWaae
WaaeaacaWG4baacaGLOaGaayzkaaGaeyypa0JaaGymaiaaicdacaWG
4bWaaWbaaSqabeaadaWcgaqaaiaaigdaaeaacaaI0aaaaaaaaaa@409D@
(concave), tandis que les composantes de l’erreur
ε
i
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacqaH1oqzda
WgaaWcbaGaamyAaaqabaaaaa@3AB2@
sont soit des réalisations
indépendantes tirées d’une loi
t
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWG0baaaa@38EA@
de Student unique à
v
=
5
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWG2bGaey
ypa0JaaGynaaaa@3AB1@
dl, ou des réalisations indépendantes tirées de
N
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWGobaaaa@38C4@
lois
t
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWG0baaaa@38EA@
de Student non centrales décalées à
v
=
5
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWG2bGaey
ypa0JaaGynaaaa@3AB1@
dl et avec paramètres de non-centralité donnés par
μ
=
15
x
i
.
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacqaH8oqBcq
GH9aqpcaaIXaGaaGynaiaadIhadaWgaaWcbaGaamyAaaqabaGccaGG
Uaaaaa@3EFA@
Les décalages appliqués aux
composantes de l’erreur dans le dernier cas font en sorte que les moyennes des
lois
t
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWG0baaaa@38EA@
de Student non centrales à partir desquelles elles sont générées
soient nulles. Les populations artificielles sont présentées aux
figures 5.1 à 5.3. En ce qui concerne les populations réelles, nous
avons pris la population
M
U
284
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWGnbGaam
yvaiaaikdacaaI4aGaaGinaaaa@3BD9@
de municipalités suédoises de Särndal et coll.
(1992) (taille de la population
N
=
284
)
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaadaqacaqaai
aad6eacqGH9aqpcaaIYaGaaGioaiaaisdaaiaawMcaaaaa@3CCE@
et considéré le logarithme
naturel de
R
M
T
85
=
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWGsbGaam
ytaiaadsfacaaI4aGaaGynaiabg2da9aaa@3CFA@
Revenus de l’imposition municipale de 1985 (en millions de couronnes)
comme variable étudiée
Y
,
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWGzbGaai
ilaaaa@397F@
et le logarithme naturel de
P
85
=
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWGqbGaaG
ioaiaaiwdacqGH9aqpaaa@3B4D@
population de 1985 (en milliers) ou de
R
E
V
84
=
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWGsbGaam
yraiaadAfacaaI4aGaaGinaiabg2da9aaa@3CF3@
valeurs immobilières selon les évaluations de 1984 (en millions de
couronnes) comme variable auxiliaire
X
.
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWGybGaai
Olaaaa@3980@
Les populations réelles sont
présentées à la figure 5.4.
Description de la figure 5.1
Figure composée de deux graphiques en nuages de point
de
y
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrFfpeea0xe9Lq=Jc9
vqaqpepm0xbbG8FasPYRqj0=yi0dXdbba9pGe9xq=JbbG8A8frFve9
Fve9Ff0dmeaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWG5baaaa@374D@
en fonction de
x ,
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrFfpeea0xe9Lq=Jc9
vqaqpepm0xbbG8FasPYRqj0=yi0dXdbba9pGe9xq=JbbG8A8frFve9
Fve9Ff0dmeaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWG4bGaai
ilaaaa@37FC@
chacun représentant une population
artificielle. Le premier graphique est la population générée à partir de
y
i
=
ε
i
,
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrFfpeea0xe9Lq=Jc9
vqaqpepm0xbbG8FasPYRqj0=yi0dXdbba9pGe9xq=JbbG8A8frFve9
Fve9Ff0dmeaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWG5bWaaS
baaSqaaiaadMgaaeqaaOGaeyypa0JaeqyTdu2aaSbaaSqaaiaadMga
aeqaaOGaaiilaaaa@3CF2@
où
ε
i
∼
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrFfpeea0xe9Lq=Jc9
vqaqpepm0xbbG8FasPYRqj0=yi0dXdbba9pGe9xq=JbbG8A8frFve9
Fve9Ff0dmeaabaqaciGacaGaaeqabaWaaeaaeaaakeaacqaH1oqzda
WgaaWcbaGaamyAaaqabaGccqWI8iIoaaa@3A43@
i.i.d.
t
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrFfpeea0xe9Lq=Jc9
vqaqpepm0xbbG8FasPYRqj0=yi0dXdbba9pGe9xq=JbbG8A8frFve9
Fve9Ff0dmeaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWG0baaaa@3748@
de
Student avec
ν = 5.
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrFfpeea0xe9Lq=Jc9
vqaqpepm0xbbG8FasPYRqj0=yi0dXdbba9pGe9xq=JbbG8A8frFve9
Fve9Ff0dmeaabaqaciGacaGaaeqabaWaaeaaeaaakeaacqaH9oGBcq
GH9aqpcaaI1aGaaiOlaaaa@3A7E@
L’axe des y
va de -4 à 8 et l’axe des x va de 0,0 à 1,0. Le nuage de point est centré
autour de
y = 0.
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpepeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peuj0lXxdrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWG5bGaey
ypa0JaaGimaiaac6caaaa@3BBF@
Le deuxième graphique en nuage de points est
la population générée à partir de
y
i
=
ε
i
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrFfpeea0xe9Lq=Jc9
vqaqpepm0xbbG8FasPYRqj0=yi0dXdbba9pGe9xq=JbbG8A8frFve9
Fve9Ff0dmeaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWG5bWaaS
baaSqaaiaadMgaaeqaaOGaeyypa0JaeqyTdu2aaSbaaSqaaiaadMga
aeqaaaaa@3C38@
et
ε
i
∼
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrFfpeea0xe9Lq=Jc9
vqaqpepm0xbbG8FasPYRqj0=yi0dXdbba9pGe9xq=JbbG8A8frFve9
Fve9Ff0dmeaabaqaciGacaGaaeqabaWaaeaaeaaakeaacqaH1oqzda
WgaaWcbaGaamyAaaqabaGccqWI8iIoaaa@3A43@
indép.
t
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrFfpeea0xe9Lq=Jc9
vqaqpepm0xbbG8FasPYRqj0=yi0dXdbba9pGe9xq=JbbG8A8frFve9
Fve9Ff0dmeaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWG0baaaa@3748@
de
Student non centrale avec
ν = 5
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrFfpeea0xe9Lq=Jc9
vqaqpepm0xbbG8FasPYRqj0=yi0dXdbba9pGe9xq=JbbG8A8frFve9
Fve9Ff0dmeaabaqaciGacaGaaeqabaWaaeaaeaaakeaacqaH9oGBcq
GH9aqpcaaI1aaaaa@39CC@
et
μ = 15
x
i
.
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrFfpeea0xe9Lq=Jc9
vqaqpepm0xbbG8FasPYRqj0=yi0dXdbba9pGe9xq=JbbG8A8frFve9
Fve9Ff0dmeaabaqaciGacaGaaeqabaWaaeaaeaaakeaacqaH8oqBcq
GH9aqpcaaIXaGaaGynaiaadIhadaWgaaWcbaGaamyAaaqabaGccaGG
Uaaaaa@3D58@
L’axe des y
va de -10 à 40 et l’axe des x va de 0,0 à 1,0. Le nuage de point est
concentré autour de
y = 0
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpepeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peuj0lXxdrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWG5bGaey
ypa0JaaGimaaaa@3B0D@
pour de petites valeurs de
x .
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpepeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peuj0lXxdrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWG4bGaai
Olaaaa@39FE@
Plus
x
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpepeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peuj0lXxdrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWG4baaaa@394C@
augmente, plus la dispersion
des points augmente.
Description de la figure 5.2
Figure composée de deux graphiques en nuages de point
de
y
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrFfpeea0xe9Lq=Jc9
vqaqpepm0xbbG8FasPYRqj0=yi0dXdbba9pGe9xq=JbbG8A8frFve9
Fve9Ff0dmeaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWG5baaaa@374D@
en fonction de
x ,
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrFfpeea0xe9Lq=Jc9
vqaqpepm0xbbG8FasPYRqj0=yi0dXdbba9pGe9xq=JbbG8A8frFve9
Fve9Ff0dmeaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWG4bGaai
ilaaaa@37FC@
chacun représentant une population
artificielle. Le premier graphique est la population générée à partir de
y
i
= 10
x
i
+
ε
i
,
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrFfpeea0xe9Lq=Jc9
vqaqpepm0xbbG8FasPYRqj0=yi0dXdbba9pGe9xq=JbbG8A8frFve9
Fve9Ff0dmeaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWG5bWaaS
baaSqaaiaadMgaaeqaaOGaeyypa0JaaGymaiaaicdacaWG4bWaaSba
aSqaaiaadMgaaeqaaOGaey4kaSIaeqyTdu2aaSbaaSqaaiaadMgaae
qaaOGaaiilaaaa@416A@
où
ε
i
∼
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrFfpeea0xe9Lq=Jc9
vqaqpepm0xbbG8FasPYRqj0=yi0dXdbba9pGe9xq=JbbG8A8frFve9
Fve9Ff0dmeaabaqaciGacaGaaeqabaWaaeaaeaaakeaacqaH1oqzda
WgaaWcbaGaamyAaaqabaGccqWI8iIoaaa@3A43@
i.i.d.
t
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrFfpeea0xe9Lq=Jc9
vqaqpepm0xbbG8FasPYRqj0=yi0dXdbba9pGe9xq=JbbG8A8frFve9
Fve9Ff0dmeaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWG0baaaa@3748@
de
Student avec
ν = 5.
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrFfpeea0xe9Lq=Jc9
vqaqpepm0xbbG8FasPYRqj0=yi0dXdbba9pGe9xq=JbbG8A8frFve9
Fve9Ff0dmeaabaqaciGacaGaaeqabaWaaeaaeaaakeaacqaH9oGBcq
GH9aqpcaaI1aGaaiOlaaaa@3A7E@
L’axe des y va de 0 à 10 et l’axe des x va de
0,0 à 1,0. Le nuage de point montre une relation linéaire croissante entre
x
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpepeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peuj0lXxdrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWG4baaaa@394C@
et
y .
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpepeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peuj0lXxdrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWG5bGaai
Olaaaa@39FF@
Le deuxième graphique en nuage
de points est la population générée à partir de
y
i
=
ε
i
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrFfpeea0xe9Lq=Jc9
vqaqpepm0xbbG8FasPYRqj0=yi0dXdbba9pGe9xq=JbbG8A8frFve9
Fve9Ff0dmeaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWG5bWaaS
baaSqaaiaadMgaaeqaaOGaeyypa0JaeqyTdu2aaSbaaSqaaiaadMga
aeqaaaaa@3C38@
et
ε
i
∼
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrFfpeea0xe9Lq=Jc9
vqaqpepm0xbbG8FasPYRqj0=yi0dXdbba9pGe9xq=JbbG8A8frFve9
Fve9Ff0dmeaabaqaciGacaGaaeqabaWaaeaaeaaakeaacqaH1oqzda
WgaaWcbaGaamyAaaqabaGccqWI8iIoaaa@3A43@
indép.
t
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrFfpeea0xe9Lq=Jc9
vqaqpepm0xbbG8FasPYRqj0=yi0dXdbba9pGe9xq=JbbG8A8frFve9
Fve9Ff0dmeaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWG0baaaa@3748@
de
Student non centrale avec
ν = 5
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrFfpeea0xe9Lq=Jc9
vqaqpepm0xbbG8FasPYRqj0=yi0dXdbba9pGe9xq=JbbG8A8frFve9
Fve9Ff0dmeaabaqaciGacaGaaeqabaWaaeaaeaaakeaacqaH9oGBcq
GH9aqpcaaI1aaaaa@39CC@
et
μ = 15
x
i
.
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrFfpeea0xe9Lq=Jc9
vqaqpepm0xbbG8FasPYRqj0=yi0dXdbba9pGe9xq=JbbG8A8frFve9
Fve9Ff0dmeaabaqaciGacaGaaeqabaWaaeaaeaaakeaacqaH8oqBcq
GH9aqpcaaIXaGaaGynaiaadIhadaWgaaWcbaGaamyAaaqabaGccaGG
Uaaaaa@3D58@
L’axe des y
va de 0 à 50 et l’axe des x va de 0,0 à 1,0. Le nuage de point montre une
relation linéaire croissante entre
x
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpepeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peuj0lXxdrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWG4baaaa@394C@
et
y .
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpepeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peuj0lXxdrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWG5bGaai
Olaaaa@39FF@
Plus
x
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpepeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peuj0lXxdrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWG4baaaa@394C@
augmente, plus la dispersion
des points augmente.
Description de la figure 5.3
Figure composée de deux graphiques en nuages de point
de
y
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrFfpeea0xe9Lq=Jc9
vqaqpepm0xbbG8FasPYRqj0=yi0dXdbba9pGe9xq=JbbG8A8frFve9
Fve9Ff0dmeaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWG5baaaa@374D@
en fonction de
x ,
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrFfpeea0xe9Lq=Jc9
vqaqpepm0xbbG8FasPYRqj0=yi0dXdbba9pGe9xq=JbbG8A8frFve9
Fve9Ff0dmeaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWG4bGaai
ilaaaa@37FC@
chacun représentant une population
artificielle. Le premier graphique est la population générée à partir de
y
i
= 10
x
i
1 / 4
+
ε
i
,
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrFfpeea0xe9Lq=Jc9
vqaqpepm0xbbG8FasPYRqj0=yi0dXdbba9pGe9xq=JbbG8A8frFve9
Fve9Ff0dmeaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWG5bWaaS
baaSqaaiaadMgaaeqaaOGaeyypa0JaaGymaiaaicdacaWG4bWaa0ba
aSqaaiaadMgaaeaadaWcgaqaaiaaigdaaeaacaaI0aaaaaaakiabgU
caRiabew7aLnaaBaaaleaacaWGPbaabeaakiaacYcaaaa@42FA@
où
ε
i
∼
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrFfpeea0xe9Lq=Jc9
vqaqpepm0xbbG8FasPYRqj0=yi0dXdbba9pGe9xq=JbbG8A8frFve9
Fve9Ff0dmeaabaqaciGacaGaaeqabaWaaeaaeaaakeaacqaH1oqzda
WgaaWcbaGaamyAaaqabaGccqWI8iIoaaa@3A43@
i.i.d.
t
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrFfpeea0xe9Lq=Jc9
vqaqpepm0xbbG8FasPYRqj0=yi0dXdbba9pGe9xq=JbbG8A8frFve9
Fve9Ff0dmeaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWG0baaaa@3748@
de
Student avec
ν = 5.
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrFfpeea0xe9Lq=Jc9
vqaqpepm0xbbG8FasPYRqj0=yi0dXdbba9pGe9xq=JbbG8A8frFve9
Fve9Ff0dmeaabaqaciGacaGaaeqabaWaaeaaeaaakeaacqaH9oGBcq
GH9aqpcaaI1aGaaiOlaaaa@3A7E@
L’axe des y
va de 0 à 15 et l’axe des x va de 0,0 à 1,0. Le nuage de point montre une
relation concave croissante entre
x
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpepeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peuj0lXxdrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWG4baaaa@394C@
et
y .
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpepeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peuj0lXxdrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWG5bGaai
Olaaaa@39FF@
Le deuxième graphique en nuage
de points est la population générée à partir de
y
i
=
ε
i
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrFfpeea0xe9Lq=Jc9
vqaqpepm0xbbG8FasPYRqj0=yi0dXdbba9pGe9xq=JbbG8A8frFve9
Fve9Ff0dmeaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWG5bWaaS
baaSqaaiaadMgaaeqaaOGaeyypa0JaeqyTdu2aaSbaaSqaaiaadMga
aeqaaaaa@3C38@
et
ε
i
∼
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrFfpeea0xe9Lq=Jc9
vqaqpepm0xbbG8FasPYRqj0=yi0dXdbba9pGe9xq=JbbG8A8frFve9
Fve9Ff0dmeaabaqaciGacaGaaeqabaWaaeaaeaaakeaacqaH1oqzda
WgaaWcbaGaamyAaaqabaGccqWI8iIoaaa@3A43@
indép.
t
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrFfpeea0xe9Lq=Jc9
vqaqpepm0xbbG8FasPYRqj0=yi0dXdbba9pGe9xq=JbbG8A8frFve9
Fve9Ff0dmeaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWG0baaaa@3748@
de
Student non centrale avec
ν = 5
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrFfpeea0xe9Lq=Jc9
vqaqpepm0xbbG8FasPYRqj0=yi0dXdbba9pGe9xq=JbbG8A8frFve9
Fve9Ff0dmeaabaqaciGacaGaaeqabaWaaeaaeaaakeaacqaH9oGBcq
GH9aqpcaaI1aaaaa@39CC@
et
μ = 15
x
i
.
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrFfpeea0xe9Lq=Jc9
vqaqpepm0xbbG8FasPYRqj0=yi0dXdbba9pGe9xq=JbbG8A8frFve9
Fve9Ff0dmeaabaqaciGacaGaaeqabaWaaeaaeaaakeaacqaH8oqBcq
GH9aqpcaaIXaGaaGynaiaadIhadaWgaaWcbaGaamyAaaqabaGccaGG
Uaaaaa@3D58@
L’axe des y va de 0 à 50 et l’axe des x va de
0,0 à 1,0. Le nuage de point montre une relation concave croissante entre
x
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpepeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peuj0lXxdrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWG4baaaa@394C@
et
y .
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpepeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peuj0lXxdrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWG5bGaai
Olaaaa@39FF@
Plus
x
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpepeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peuj0lXxdrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWG4baaaa@394C@
augmente, plus la dispersion
des points augmente.
Description de la figure 5.4
Figure composée de deux graphiques en nuages de point
de
y
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrFfpeea0xe9Lq=Jc9
vqaqpepm0xbbG8FasPYRqj0=yi0dXdbba9pGe9xq=JbbG8A8frFve9
Fve9Ff0dmeaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWG5baaaa@374D@
en fonction de
x ,
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrFfpeea0xe9Lq=Jc9
vqaqpepm0xbbG8FasPYRqj0=yi0dXdbba9pGe9xq=JbbG8A8frFve9
Fve9Ff0dmeaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWG4bGaai
ilaaaa@37FC@
chacun représentant une population réelle, population
M U 284
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrFfpeea0xe9Lq=Jc9
vqaqpepm0xbbG8FasPYRqj0=yi0dXdbba9pGe9xq=JbbG8A8frFve9
Fve9Ff0dmeaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWGnbGaam
yvaiaaikdacaaI4aGaaGinaaaa@3A37@
de
municipalités suédoises de Särndal et coll. (1992). Dans le premier graphique,
y
i
= ln R M T
85
i
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrFfpeea0xe9Lq=Jc9
vqaqpepm0xbbG8FasPYRqj0=yi0dXdbba9pGe9xq=JbbG8A8frFve9
Fve9Ff0dmeaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWG5bWaaS
baaSqaaiaadMgaaeqaaOGaeyypa0JaciiBaiaac6gacaWGsbGaamyt
aiaadsfacaaI4aGaaGynamaaBaaaleaacaWGPbaabeaaaaa@4078@
pour la
i
e
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrFfpeea0xe9Lq=Jc9
vqaqpepm0xbbG8FasPYRqj0=yi0dXdbba9pGe9xq=JbbG8A8frFve9
Fve9Ff0dmeaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWGPbWaaW
baaSqabeaacaqGLbaaaaaa@3852@
municipalité et
x
i
= ln P
85
i
.
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrFfpeea0xe9Lq=Jc9
vqaqpepm0xbbG8FasPYRqj0=yi0dXdbba9pGe9xq=JbbG8A8frFve9
Fve9Ff0dmeaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWG4bWaaS
baaSqaaiaadMgaaeqaaOGaeyypa0JaciiBaiaac6gacaWGqbGaaGio
aiaaiwdadaWgaaWcbaGaamyAaaqabaGccaGGUaaaaa@3F86@
L’axe des y va de 3 à 9 et l’axe des x va de 1
à 6. Le nuage de point montre une relation linéaire croissante entre
x
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpepeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peuj0lXxdrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWG4baaaa@394C@
et
y .
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpepeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peuj0lXxdrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWG5bGaai
Olaaaa@39FF@
Dans le deuxième graphique,
y
i
= ln R M T
85
i
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrFfpeea0xe9Lq=Jc9
vqaqpepm0xbbG8FasPYRqj0=yi0dXdbba9pGe9xq=JbbG8A8frFve9
Fve9Ff0dmeaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWG5bWaaS
baaSqaaiaadMgaaeqaaOGaeyypa0JaciiBaiaac6gacaWGsbGaamyt
aiaadsfacaaI4aGaaGynamaaBaaaleaacaWGPbaabeaaaaa@4078@
pour la
i
e
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrFfpeea0xe9Lq=Jc9
vqaqpepm0xbbG8FasPYRqj0=yi0dXdbba9pGe9xq=JbbG8A8frFve9
Fve9Ff0dmeaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWGPbWaaW
baaSqabeaacaqGLbaaaaaa@3852@
municipalité et
x
i
= ln R E V
84
i
.
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrFfpeea0xe9Lq=Jc9
vqaqpepm0xbbG8FasPYRqj0=yi0dXdbba9pGe9xq=JbbG8A8frFve9
Fve9Ff0dmeaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWG4bWaaS
baaSqaaiaadMgaaeqaaOGaeyypa0JaciiBaiaac6gacaWGsbGaamyr
aiaadAfacaaI4aGaaGinamaaBaaaleaacaWGPbaabeaakiaac6caaa
a@412C@
L’axe des y va de 3 à 9 et l’axe des x va de 6 à 11.
Le nuage de point montre une relation linéaire croissante entre
x
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpepeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peuj0lXxdrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWG4baaaa@394C@
et
y ,
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpepeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peuj0lXxdrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWG5bGaai
ilaaaa@39FD@
mais plus dispersée.
Pour chaque population, nous avons sélectionné indépendamment
B
=
1
000
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWGcbGaey
ypa0JaaGymaiaaysW7caaIWaGaaGimaiaaicdaaaa@3E34@
échantillons. Pour le tirage
d’échantillons à partir des populations artificielles, en cas d’échantillonnage
aléatoire simple sans remise, nous avons fixé la taille d’échantillon à
n
=
100
,
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWGUbGaey
ypa0JaaGymaiaaicdacaaIWaGaaiilaaaa@3CC9@
et en cas d’échantillonnage
de Poisson, nous avons fixé la taille d’échantillon espérée à
n
*
=
100
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWGUbWaaW
baaSqabeaacaGGQaaaaOGaeyypa0JaaGymaiaaicdacaaIWaaaaa@3CFE@
et fait en sorte que les
probabilités d’inclusion dans l’échantillon soient proportionnelles aux
écarts-types des lois
t
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWG0baaaa@38EA@
de Student non centrales
décalées susmentionnées. Pour le tirage d’échantillons dans les populations
réelles, nous avons fixé la taille d’échantillon à
n
=
30
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWGUbGaey
ypa0JaaG4maiaaicdaaaa@3B61@
en cas d’échantillonnage
aléatoire simple sans remise. Pour l’échantillonnage de Poisson, nous avons
fixé la taille d’échantillon espérée à
n
*
=
30
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWGUbWaaW
baaSqabeaacaGGQaaaaOGaeyypa0JaaG4maiaaicdaaaa@3C46@
et fait en sorte que les
probabilités d’inclusion dans l’échantillon soient proportionnelles aux valeurs
absolues des résidus des régressions linéaires par les moindres carrés des
valeurs
y
i
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWG5bWaaS
baaSqaaiaadMgaaeqaaaaa@3A09@
de la population sur les
valeurs
x
i
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWG4bWaaS
baaSqaaiaadMgaaeqaaaaa@3A08@
de la population.
Comme pour la définition des estimateurs non paramétriques, nous
avons utilisé la fonction noyau d’Epanechnikov
K
(
u
)
:
=
0,75
(
1
−
u
2
)
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWGlbWaae
WaaeaacaWG1baacaGLOaGaayzkaaGaaiOoaiabg2da9iaabcdacaqG
SaGaae4naiaabwdadaqadaqaaiaaigdacqGHsislcaWG1bWaaWbaaS
qabeaacaaIYaaaaaGccaGLOaGaayzkaaaaaa@44FA@
avec
λ
=
0,15
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacqaH7oaBcq
GH9aqpcaqGWaGaaeilaiaabgdacaqG1aaaaa@3D79@
ou
λ
=
0,3
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacqaH7oaBcq
GH9aqpcaqGWaGaaeilaiaabodaaaa@3CC3@
pour les échantillons tirés
des populations artificielles et la fonction noyau gaussienne
K
(
u
)
:
=
1
/
2
π
e
−
(
1
/
2
)
u
2
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWGlbWaae
WaaeaacaWG1baacaGLOaGaayzkaaGaaiOoaiabg2da9maalyaabaGa
aGymaaqaamaakaaabaGaaGOmaiabec8aWbWcbeaakiaadwgadaahaa
WcbeqaaiabgkHiTmaabmaabaWaaSGbaeaacaaIXaaabaGaaGOmaaaa
aiaawIcacaGLPaaacaWG1bWaaWbaaWqabeaacaaIYaaaaaaaaaaaaa@4775@
avec
λ
=
1
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacqaH7oaBcq
GH9aqpcaaIXaaaaa@3B66@
ou
λ
=
2
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacqaH7oaBcq
GH9aqpcaaIYaaaaa@3B67@
pour les échantillons tirés
des populations réelles. Dans les tableaux présentant les résultats des
simulations, les estimateurs non paramétriques correspondant aux petites et aux
grandes valeurs de fenêtre de lissage sont désignés par un
s
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWGZbaaaa@38E9@
(pour small ) ou par un
l
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWGSbaaaa@38E2@
(pour large ), respectivement, dans l’indice inférieur. Nous avons recouru
à la fonction noyau gaussienne pour les échantillons tirés des populations
réelles afin d’éviter les problèmes de singularité qui se posent en cas de
vides dans le jeu de valeurs
x
i
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWG4bWaaS
baaSqaaiaadMgaaeqaaaaa@3A08@
échantillonnées. De tels
vides sont nettement plus susceptibles d’exister dans le cas des populations
réelles que dans celui des populations artificielles, parce que les lois des
variables auxiliaires sont asymétriques dans les premières. En fait, dans les
populations artificielles, les estimateurs non paramétriques étaient bien
définis pour chacun des
B
=
1
000
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWGcbGaey
ypa0JaaGymaiaaysW7caaIWaGaaGimaiaaicdaaaa@3E34@
échantillons sélectionnés
selon le plan d’échantillonnage aléatoire simple sans remise. Pour le plan
d’échantillonnage de Poisson, par contre, 47 des
B
=
1
000
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWGcbGaey
ypa0JaaGymaiaaysW7caaIWaGaaGimaiaaicdaaaa@3E34@
échantillons simulés étaient
tels que les estimateurs non paramétriques avec la petite valeur de fenêtre de
lissage n’ont pas pu être calculés et seulement un de ces échantillons
était tel que les estimateurs non paramétriques avec la grande valeur de fenêtre
de lissage étaient indéfinis. Les résultats des simulations s’appliquant aux
estimateurs non paramétriques dans les tableaux 5.2 et 5.5 tiennent compte
uniquement des échantillons pour lesquels
les estimateurs étaient bien définis et sont donc fondés sur un peu moins que
les
B
=
1
000
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWGcbGaey
ypa0JaaGymaiaaysW7caaIWaGaaGimaiaaicdaaaa@3E34@
réalisations.
Les tableaux 5.1 à 5.4 donnent le biais simulé (BIAIS) et la racine
carrée de l’erreur quadratique moyenne simulée (REQM) pour chaque estimateur de
la fonction de répartition à différents niveaux de
t
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWG0baaaa@38EA@
auxquels
F
N
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWGgbWaaS
baaSqaaiaad6eaaeqaaOWaaeWaaeaacaWG0baacaGLOaGaayzkaaaa
aa@3C47@
a été estimée : en se
basant, par exemple, sur les valeurs
F
˜
b
(
t
)
,
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaaceWGgbGbaG
aadaWgaaWcbaGaamOyaaqabaGcdaqadaqaaiaadshaaiaawIcacaGL
PaaacaGGSaaaaa@3D1A@
b
=
1
,
2
,
…
,
B
,
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWGIbGaey
ypa0JaaGymaiaacYcacaaIYaGaaiilaiablAciljaacYcacaWGcbGa
aiilaaaa@3FFE@
tirées de l’estimateur
F
˜
(
t
)
,
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaaceWGgbGbaG
aadaqadaqaaiaadshaaiaawIcacaGLPaaacaGGSaaaaa@3BFD@
BIAIS
:
=
1
B
∑
b
=
1
B
(
F
˜
b
(
t
)
−
F
N
(
t
)
)
×
10
000
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaqGcbGaae
ysaiaabgeacaqGjbGaae4uaiaacQdacqGH9aqpdaWcaaqaaiaaigda
aeaacaWGcbaaamaaqahabaWaaeWaaeaaceWGgbGbaGaadaWgaaWcba
GaamOyaaqabaGcdaqadaqaaiaadshaaiaawIcacaGLPaaacqGHsisl
caWGgbWaaSbaaSqaaiaad6eaaeqaaOWaaeWaaeaacaWG0baacaGLOa
GaayzkaaaacaGLOaGaayzkaaGaey41aqRaaGymaiaaicdacaaMe8Ua
aGimaiaaicdacaaIWaaaleaacaWGIbGaeyypa0JaaGymaaqaaiaadk
eaa0GaeyyeIuoaaaa@577B@
et
REQM
:
=
1
B
∑
b
=
1
B
(
F
˜
b
(
t
)
−
F
N
(
t
)
)
2
×
10
000.
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaqGsbGaae
yraiaabgfacaqGnbGaaiOoaiabg2da9maakaaabaWaaSaaaeaacaaI
XaaabaGaamOqaaaadaaeWbqaamaabmaabaGabmOrayaaiaWaaSbaaS
qaaiaadkgaaeqaaOWaaeWaaeaacaWG0baacaGLOaGaayzkaaGaeyOe
I0IaamOramaaBaaaleaacaWGobaabeaakmaabmaabaGaamiDaaGaay
jkaiaawMcaaaGaayjkaiaawMcaamaaCaaaleqabaGaaGOmaaaaaeaa
caWGIbGaeyypa0JaaGymaaqaaiaadkeaa0GaeyyeIuoaaSqabaGccq
GHxdaTcaaIXaGaaGimaiaaysW7caaIWaGaaGimaiaaicdacaGGUaaa
aa@5879@
La REQM montre que les estimateurs fondés sur les
valeurs prédites modifiées sont habituellement plus efficaces. Dans le cas de
l'échantillonnage dans les populations réelles, l'augmentation des REQM est
parfois assez grande. Comme prévu, les estimateurs fondés sur le modèle ont
tendance à être plus efficaces que les estimateurs par la différence
généralisée sous échantillonnage aléatoire simple sans remise quand les deux
types d’estimateurs sont approximativement sans biais. Sous échantillonnage de
Poisson, le BIAIS des estimateurs fondés sur le modèle augmente, mais demeure
néanmoins concurrentiel. Une plus grande variabilité des probabilités
d’inclusion dans l’échantillon modifierait certainement ce résultat, car elle augmenterait
le BIAIS des estimateurs fondés sur le modèle. Les résultats des simulations ne
doivent donc pas être considérés comme contredisant Johnson, Breidt et Opsomer
(2008) qui se prononcent en faveur des estimateurs par la différence
généralisée (appelés estimateurs assistés par modèle dans leur article),
soutenant qu’il s’agit d’« un bon choix global pour les estimateurs de la
fonction de répartition ».
Tableau 5.1
Populations artificielles (taille de population
N
=
1 000
)
.
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqipu0Je9sqqrpepC0xbbL8F4rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbeqabeWacmGabiqabeqabmqabeabbaGcbaWaaeGaaeaaca
WGobGaaGypaiaabgdacaqGSaGaaeimaiaabcdacaqGWaaacaGLPaaa
caGGUaaaaa@3B88@
BIAIS et REQM des estimateurs de la fonction de répartition sous échantillonnage aléatoire simple sans remise. Taille d’échantillon
n
=
100
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqipu0Je9sqqrpepC0xbbL8F4rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbeqabeWacmGabiqabeqabmqabeabbaGcbaGaamOBaiaai2
dacaqGXaGaaeimaiaabcdaaaa@38CC@
Sommaire du tableau
Le tableau montre les résultats de Tableau 5.1
Populations artificielles (taille de population XXXX). BIAIS et REQM des estimateurs de la fonction de répartition sous échantillonnage aléatoire simple sans remise. Taille d’échantillon XXXX
XXXX , XXXX, BIAIS , REQM et REQM , calculées selon XXXX avec XXXX i.i.d. de Student centrale XXXX avec XXXX, XXXX avec XXXX indép. de Student non centrale XXXX avec XXXX et XXXX, XXXX avec XXXX i.i.d. de Student XXXX avec XXXX, XXXX avec XXXX indép. de Student non centrale XXXX avec XXXX et XXXX, XXXX avec XXXX i.i.d. de Student XXXX avec XXXX et XXXX avec XXXX indép. de Student non centrale XXXX avec XXXX et XXXX unités de mesure (figurant comme en-tête de colonne).
t
=
F
N
−
1
(
0,05
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbeqabeWacmGabiqabeqabmqabeabbaGcbaGaamiDaiaai2
dacaWGgbWaa0baaSqaaiaad6eaaeaacqGHsislcaaIXaaaaOWaaeWa
aeaacaaIWaGaaGOlaiaaicdacaaI1aaacaGLOaGaayzkaaaaaa@40DB@
t
=
F
N
−
1
(
0,25
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbeqabeWacmGabiqabeqabmqabeabbaGcbaGaamiDaiaai2
dacaWGgbWaa0baaSqaaiaad6eaaeaacqGHsislcaaIXaaaaOWaaeWa
aeaacaaIWaGaaGOlaiaaikdacaaI1aaacaGLOaGaayzkaaaaaa@40DD@
t
=
F
N
−
1
(
0,50
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbeqabeWacmGabiqabeqabmqabeabbaGcbaGaamiDaiaai2
dacaWGgbWaa0baaSqaaiaad6eaaeaacqGHsislcaaIXaaaaOWaaeWa
aeaacaaIWaGaaGOlaiaaiwdacaaIWaaacaGLOaGaayzkaaaaaa@40DB@
t
=
F
N
−
1
(
0,75
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbeqabeWacmGabiqabeqabmqabeabbaGcbaGaamiDaiaai2
dacaWGgbWaa0baaSqaaiaad6eaaeaacqGHsislcaaIXaaaaOWaaeWa
aeaacaaIWaGaaGOlaiaaiEdacaaI1aaacaGLOaGaayzkaaaaaa@40E2@
t
=
F
N
−
1
(
0,95
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbeqabeWacmGabiqabeqabmqabeabbaGcbaGaamiDaiaai2
dacaWGgbWaa0baaSqaaiaad6eaaeaacqGHsislcaaIXaaaaOWaaeWa
aeaacaaIWaGaaGOlaiaaiMdacaaI1aaacaGLOaGaayzkaaaaaa@40E4@
BIAIS
REQM
BIAIS
REQM
BIAIS
REQM
BIAIS
REQM
BIAIS
REQM
y
i
=
ε
i
,
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGWjLspw0le9v8qqaqFD0xXdHaVhbbf9y8qqaqFr0xc9qq
Fr0dXdbvb9frpepee9k8hqNsFf0=qqfqpeFne9qq=xd9qqaq=Jf9sr
0=vr0=vrWZqaaeaabiGaciaacaqabeaadaqaaqaaaOqaaiaadMhada
WgaaWcbaGaamyAaaqabaGccqGH9aqpcqaH1oqzdaWgaaWcbaGaamyA
aaqabaGccaGGSaaaaa@419E@
avec
ε
i
∼
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGWjLspw0le9v8qqaqFD0xXdHaVhbbf9y8qqaqFr0xc9qq
Fr0dXdbvb9frpepee9k8hqNsFf0=qqfqpeFne9qq=xd9qqaq=Jf9sr
0=vr0=vrWZqaaeaabiGaciaacaqabeaadaqaaqaaaOqaaiabew7aLn
aaBaaaleaacaWGPbaabeaakiablYJi6aaa@3EEF@
i.i.d.
t
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaamiDaaaa@3819@
de Student centrale avec
ν
=
5
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaeqyVd4MaaG
ypaiaaiwdaaaa@3A5E@
F
^
s
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaja
WaaSbaaSqaaiaadohaaeqaaOWaaeWaaeaacaWG0baacaGLOaGaayzk
aaaaaa@3BAB@
6
216
-3
433
31
512
23
434
12
207
F
^
l
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaja
WaaSbaaSqaaiaadYgaaeqaaOWaaeWaaeaacaWG0baacaGLOaGaayzk
aaaaaa@3BA4@
15
219
10
430
0
502
-10
429
3
213
F
^
s
*
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGWjLspw0le9v8qqaqFD0xXdHaVhbbf9y8qqaqFr0xc9qq
Fr0dXdbvb9frpepee9k8hqNsFf0=qqfqpeFne9qq=xd9qqaq=Jf9sr
0=vr0=vrWZqaaeaabiGaciaacaqabeaadaqaaqaaaOqaaiqadAeaga
qcamaaDaaaleaacaWGZbaabaGaaiOkaaaakmaabmaabaGaamiDaaGa
ayjkaiaawMcaaaaa@4034@
6
209
-30
411
22
484
22
414
3
200
F
^
l
*
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaja
Waa0baaSqaaiaadYgaaeaacaaIQaaaaOWaaeWaaeaacaWG0baacaGL
OaGaayzkaaaaaa@3C59@
15
214
-9
409
10
477
1
407
-10
207
F
˜
s
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaia
WaaSbaaSqaaiaadohaaeqaaOWaaeWaaeaacaWG0baacaGLOaGaayzk
aaaaaa@3BAA@
6
213
8
425
24
504
-4
430
8
207
F
˜
l
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaia
WaaSbaaSqaaiaadYgaaeqaaOWaaeWaaeaacaWG0baacaGLOaGaayzk
aaaaaa@3BA3@
6
210
10
417
22
494
-8
422
6
206
F
˜
s
*
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaia
Waa0baaSqaaiaadohaaeaacaaIQaaaaOWaaeWaaeaacaWG0baacaGL
OaGaayzkaaaaaa@3C5F@
8
213
9
426
25
503
-5
432
5
206
F
˜
l
*
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaia
Waa0baaSqaaiaadYgaaeaacaaIQaaaaOWaaeWaaeaacaWG0baacaGL
OaGaayzkaaaaaa@3C58@
7
210
10
417
23
494
-6
424
4
206
F
˜
π
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaia
WaaSbaaSqaaiabec8aWbqabaGcdaqadaqaaiaadshaaiaawIcacaGL
Paaaaaa@3C6F@
7
208
11
411
19
489
-5
417
6
200
y
i
=
ε
i
,
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaamyEamaaBa
aaleaacaWGPbaabeaakiaai2dacqaH1oqzdaWgaaWcbaGaamyAaaqa
baGccaGGSaaaaa@3D84@
avec
ε
i
∼
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaeqyTdu2aaS
baaSqaaiaadMgaaeqaaOGaeSipIOdaaa@3B14@
indép.
t
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaamiDaaaa@3819@
de Student non centrale avec
ν
=
5
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaeqyVd4MaaG
ypaiaaiwdaaaa@3A5E@
et
μ
=
15
x
i
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaeqiVd0MaaG
ypaiaaigdacaaI1aGaamiEamaaBaaaleaacaWGPbaabeaaaaa@3D2E@
F
^
s
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaja
WaaSbaaSqaaiaadohaaeqaaOWaaeWaaeaacaWG0baacaGLOaGaayzk
aaaaaa@3BAB@
26
225
33
376
8
477
26
419
33
209
F
^
l
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaja
WaaSbaaSqaaiaadYgaaeqaaOWaaeWaaeaacaWG0baacaGLOaGaayzk
aaaaaa@3BA4@
52
236
23
374
-5
475
38
421
29
213
F
^
s
*
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaja
Waa0baaSqaaiaadohaaeaacaaIQaaaaOWaaeWaaeaacaWG0baacaGL
OaGaayzkaaaaaa@3C60@
20
195
-29
351
-89
471
11
407
30
202
F
^
l
*
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaja
Waa0baaSqaaiaadYgaaeaacaaIQaaaaOWaaeWaaeaacaWG0baacaGL
OaGaayzkaaaaaa@3C59@
36
201
-11
357
-94
473
28
410
21
204
F
˜
s
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaia
WaaSbaaSqaaiaadohaaeqaaOWaaeWaaeaacaWG0baacaGLOaGaayzk
aaaaaa@3BAA@
8
211
11
370
-7
473
4
415
16
211
F
˜
l
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaia
WaaSbaaSqaaiaadYgaaeqaaOWaaeWaaeaacaWG0baacaGLOaGaayzk
aaaaaa@3BA3@
5
208
8
367
-5
468
5
411
16
212
F
˜
s
*
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaia
Waa0baaSqaaiaadohaaeaacaaIQaaaaOWaaeWaaeaacaWG0baacaGL
OaGaayzkaaaaaa@3C5F@
11
210
11
372
-11
475
4
416
15
210
F
˜
l
*
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaia
Waa0baaSqaaiaadYgaaeaacaaIQaaaaOWaaeWaaeaacaWG0baacaGL
OaGaayzkaaaaaa@3C58@
7
208
11
368
-7
468
8
412
15
211
F
˜
π
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaia
WaaSbaaSqaaiabec8aWbqabaGcdaqadaqaaiaadshaaiaawIcacaGL
Paaaaaa@3C6F@
1
211
1
391
-6
477
8
399
18
210
y
i
=
10
x
i
+
ε
i
,
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaamyEamaaBa
aaleaacaWGPbaabeaakiaai2dacaaIXaGaaGimaiaadIhadaWgaaWc
baGaamyAaaqabaGccqGHRaWkcqaH1oqzdaWgaaWcbaGaamyAaaqaba
GccaGGSaaaaa@41FC@
avec
ε
i
∼
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaeqyTdu2aaS
baaSqaaiaadMgaaeqaaOGaeSipIOdaaa@3B14@
i.i.d.
t
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaamiDaaaa@3819@
de Student avec
ν
=
5
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaeqyVd4MaaG
ypaiaaiwdaaaa@3A5E@
F
^
s
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaja
WaaSbaaSqaaiaadohaaeqaaOWaaeWaaeaacaWG0baacaGLOaGaayzk
aaaaaa@3BAB@
32
201
25
275
13
250
-14
264
-36
217
F
^
l
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaja
WaaSbaaSqaaiaadYgaaeqaaOWaaeWaaeaacaWG0baacaGLOaGaayzk
aaaaaa@3BA4@
114
250
152
304
12
236
-180
312
-86
242
F
^
s
*
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaja
Waa0baaSqaaiaadohaaeaacaaIQaaaaOWaaeWaaeaacaWG0baacaGL
OaGaayzkaaaaaa@3C60@
-50
165
12
226
51
216
26
230
13
172
F
^
l
*
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaja
Waa0baaSqaaiaadYgaaeaacaaIQaaaaOWaaeWaaeaacaWG0baacaGL
OaGaayzkaaaaaa@3C59@
-46
155
-14
199
69
195
23
211
17
156
F
˜
s
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaia
WaaSbaaSqaaiaadohaaeqaaOWaaeWaaeaacaWG0baacaGLOaGaayzk
aaaaaa@3BAA@
-5
186
4
275
15
248
11
269
-2
201
F
˜
l
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaia
WaaSbaaSqaaiaadYgaaeqaaOWaaeWaaeaacaWG0baacaGLOaGaayzk
aaaaaa@3BA3@
-5
184
7
274
17
250
5
269
-2
196
F
˜
s
*
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaia
Waa0baaSqaaiaadohaaeaacaaIQaaaaOWaaeWaaeaacaWG0baacaGL
OaGaayzkaaaaaa@3C5F@
-10
180
5
275
16
245
14
266
-1
200
F
˜
l
*
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaia
Waa0baaSqaaiaadYgaaeaacaaIQaaaaOWaaeWaaeaacaWG0baacaGL
OaGaayzkaaaaaa@3C58@
-9
176
3
272
15
242
13
262
-1
194
F
˜
π
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaia
WaaSbaaSqaaiabec8aWbqabaGcdaqadaqaaiaadshaaiaawIcacaGL
Paaaaaa@3C6F@
-7
203
14
413
37
472
17
405
1
206
y
i
=
10
x
i
+
ε
i
,
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaamyEamaaBa
aaleaacaWGPbaabeaakiaai2dacaaIXaGaaGimaiaadIhadaWgaaWc
baGaamyAaaqabaGccqGHRaWkcqaH1oqzdaWgaaWcbaGaamyAaaqaba
GccaGGSaaaaa@41FC@
avec
ε
i
∼
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaeqyTdu2aaS
baaSqaaiaadMgaaeqaaOGaeSipIOdaaa@3B14@
indép.
t
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaamiDaaaa@3819@
de Student non centrale avec
ν
=
5
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaeqyVd4MaaG
ypaiaaiwdaaaa@3A5E@
et
μ
=
15
x
i
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaeqiVd0MaaG
ypaiaaigdacaaI1aGaamiEamaaBaaaleaacaWGPbaabeaaaaa@3D2E@
F
^
s
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaja
WaaSbaaSqaaiaadohaaeqaaOWaaeWaaeaacaWG0baacaGLOaGaayzk
aaaaaa@3BAB@
24
204
23
351
27
403
26
382
29
208
F
^
l
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaja
WaaSbaaSqaaiaadYgaaeqaaOWaaeWaaeaacaWG0baacaGLOaGaayzk
aaaaaa@3BA4@
94
242
135
372
51
392
13
380
15
212
F
^
s
*
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaja
Waa0baaSqaaiaadohaaeaacaaIQaaaaOWaaeWaaeaacaWG0baacaGL
OaGaayzkaaaaaa@3C60@
55
182
-9
301
-18
368
-23
359
37
202
F
^
l
*
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaja
Waa0baaSqaaiaadYgaaeaacaaIQaaaaOWaaeWaaeaacaWG0baacaGL
OaGaayzkaaaaaa@3C59@
124
210
-31
278
-63
363
-8
356
48
200
F
˜
s
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaia
WaaSbaaSqaaiaadohaaeqaaOWaaeWaaeaacaWG0baacaGLOaGaayzk
aaaaaa@3BAA@
-2
194
-4
349
11
401
18
377
13
208
F
˜
l
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaia
WaaSbaaSqaaiaadYgaaeqaaOWaaeWaaeaacaWG0baacaGLOaGaayzk
aaaaaa@3BA3@
-2
190
-5
345
12
398
17
374
11
209
F
˜
s
*
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaia
Waa0baaSqaaiaadohaaeaacaaIQaaaaOWaaeWaaeaacaWG0baacaGL
OaGaayzkaaaaaa@3C5F@
0
191
-5
352
14
401
20
376
13
207
F
˜
l
*
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaia
Waa0baaSqaaiaadYgaaeaacaaIQaaaaOWaaeWaaeaacaWG0baacaGL
OaGaayzkaaaaaa@3C58@
-1
189
-6
344
13
397
18
375
12
209
F
˜
π
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaia
WaaSbaaSqaaiabec8aWbqabaGcdaqadaqaaiaadshaaiaawIcacaGL
Paaaaaa@3C6F@
-4
205
-5
401
21
470
24
401
14
207
y
i
=
10
x
i
1
/
4
+
ε
i
,
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaamyEamaaBa
aaleaacaWGPbaabeaakiaai2dacaaIXaGaaGimaiaadIhadaqhaaWc
baGaamyAaaqaamaalyaabaGaaGymaaqaaiaaisdaaaaaaOGaey4kaS
IaeqyTdu2aaSbaaSqaaiaadMgaaeqaaOGaaiilaaaa@438C@
avec
ε
i
∼
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaeqyTdu2aaS
baaSqaaiaadMgaaeqaaOGaeSipIOdaaa@3B14@
i.i.d.
t
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaamiDaaaa@3819@
de Student avec
ν
=
5
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaeqyVd4MaaG
ypaiaaiwdaaaa@3A5E@
F
^
s
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaja
WaaSbaaSqaaiaadohaaeqaaOWaaeWaaeaacaWG0baacaGLOaGaayzk
aaaaaa@3BAB@
81
207
44
316
17
384
-2
376
23
203
F
^
l
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaja
WaaSbaaSqaaiaadYgaaeqaaOWaaeWaaeaacaWG0baacaGLOaGaayzk
aaaaaa@3BA4@
138
258
183
356
35
367
-50
374
8
208
F
^
s
*
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaja
Waa0baaSqaaiaadohaaeaacaaIQaaaaOWaaeWaaeaacaWG0baacaGL
OaGaayzkaaaaaa@3C60@
7
146
-14
274
16
352
-8
358
15
197
F
^
l
*
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaja
Waa0baaSqaaiaadYgaaeaacaaIQaaaaOWaaeWaaeaacaWG0baacaGL
OaGaayzkaaaaaa@3C59@
9
144
10
246
-2
323
-18
339
24
186
F
˜
s
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaia
WaaSbaaSqaaiaadohaaeqaaOWaaeWaaeaacaWG0baacaGLOaGaayzk
aaaaaa@3BAA@
3
175
3
319
10
383
17
374
10
203
F
˜
l
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaia
WaaSbaaSqaaiaadYgaaeqaaOWaaeWaaeaacaWG0baacaGLOaGaayzk
aaaaaa@3BA3@
0
178
5
316
11
380
17
370
8
202
F
˜
s
*
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaia
Waa0baaSqaaiaadohaaeaacaaIQaaaaOWaaeWaaeaacaWG0baacaGL
OaGaayzkaaaaaa@3C5F@
1
167
5
320
12
383
17
374
9
203
F
˜
l
*
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaia
Waa0baaSqaaiaadYgaaeaacaaIQaaaaOWaaeWaaeaacaWG0baacaGL
OaGaayzkaaaaaa@3C58@
-1
164
6
316
13
379
20
368
8
201
F
˜
π
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaia
WaaSbaaSqaaiabec8aWbqabaGcdaqadaqaaiaadshaaiaawIcacaGL
Paaaaaa@3C6F@
4
209
11
412
25
477
27
422
10
200
y
i
=
10
x
i
1
/
4
+
ε
i
,
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaamyEamaaBa
aaleaacaWGPbaabeaakiaai2dacaaIXaGaaGimaiaadIhadaqhaaWc
baGaamyAaaqaamaalyaabaGaaGymaaqaaiaaisdaaaaaaOGaey4kaS
IaeqyTdu2aaSbaaSqaaiaadMgaaeqaaOGaaiilaaaa@438C@
avec
ε
i
∼
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaeqyTdu2aaS
baaSqaaiaadMgaaeqaaOGaeSipIOdaaa@3B14@
indép.
t
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaamiDaaaa@3819@
de Student non centrale avec
ν
=
5
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaeqyVd4MaaG
ypaiaaiwdaaaa@3A5E@
et
μ
=
15
x
i
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaeqiVd0MaaG
ypaiaaigdacaaI1aGaamiEamaaBaaaleaacaWGPbaabeaaaaa@3D2E@
F
^
s
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaja
WaaSbaaSqaaiaadohaaeqaaOWaaeWaaeaacaWG0baacaGLOaGaayzk
aaaaaa@3BAB@
59
234
95
402
66
455
51
395
26
208
F
^
l
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaja
WaaSbaaSqaaiaadYgaaeqaaOWaaeWaaeaacaWG0baacaGLOaGaayzk
aaaaaa@3BA4@
94
259
190
441
147
467
98
400
16
212
F
^
s
*
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaja
Waa0baaSqaaiaadohaaeaacaaIQaaaaOWaaeWaaeaacaWG0baacaGL
OaGaayzkaaaaaa@3C60@
30
184
33
343
-123
435
-34
385
40
203
F
^
l
*
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaja
Waa0baaSqaaiaadYgaaeaacaaIQaaaaOWaaeWaaeaacaWG0baacaGL
OaGaayzkaaaaaa@3C59@
57
201
58
331
-148
437
2
382
34
203
F
˜
s
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaia
WaaSbaaSqaaiaadohaaeqaaOWaaeWaaeaacaWG0baacaGLOaGaayzk
aaaaaa@3BAA@
1
205
7
386
12
449
17
392
13
208
F
˜
l
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaia
WaaSbaaSqaaiaadYgaaeqaaOWaaeWaaeaacaWG0baacaGLOaGaayzk
aaaaaa@3BA3@
-1
204
0
385
9
445
20
389
11
209
F
˜
s
*
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaia
Waa0baaSqaaiaadohaaeaacaaIQaaaaOWaaeWaaeaacaWG0baacaGL
OaGaayzkaaaaaa@3C5F@
3
201
8
389
7
449
13
392
14
207
F
˜
l
*
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaia
Waa0baaSqaaiaadYgaaeaacaaIQaaaaOWaaeWaaeaacaWG0baacaGL
OaGaayzkaaaaaa@3C58@
0
198
6
383
9
446
19
390
13
208
F
˜
π
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaia
WaaSbaaSqaaiabec8aWbqabaGcdaqadaqaaiaadshaaiaawIcacaGL
Paaaaaa@3C6F@
0
205
-2
399
9
463
25
398
14
208
Tableau 5.2
Populations artificielles (taille de population
N = 1 000 ) .
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqipu0Je9sqqrpepC0xbbL8F4rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbeqabeWacmGabiqabeqabmqabeabbaGcbaWaaeGaaeaaca
WGobGaaGypaiaabgdacaqGSaGaaeimaiaabcdacaqGWaaacaGLPaaa
caGGUaaaaa@3B88@
BIAIS et REQM des estimateurs de la fonction de répartition sous échantillonnage de Poisson avec probabilités d’inclusion dans l’échantillon
π
i
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqipu0Je9sqqrpepC0xbbL8F4rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbeqabeWacmGabiqabeqabmqabeabbaGcbaGaeqiWda3aaS
baaSqaaiaadMgaaeqaaaaa@37CF@
proportionnelles aux écarts-types des lois
t
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqipu0Je9sqqrpepC0xbbL8F4rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbeqabeWacmGabiqabeqabmqabeabbaGcbaGaamiDaaaa@35F1@
de Student non centrales avec
ν = 5
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqipu0Je9sqqrpepC0xbbL8F4rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbeqabeWacmGabiqabeqabmqabeabbaGcbaGaeqyVd4MaaG
ypaiaaiwdaaaa@3836@
dl et avec paramètres de non-centralité
μ = 15
x
i
.
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqipu0Je9sqqrpepC0xbbL8F4rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbeqabeWacmGabiqabeqabmqabeabbaGcbaGaeqiVd0MaaG
ypaiaaigdacaaI1aGaamiEamaaBaaaleaacaWGPbaabeaakiaac6ca
aaa@3BC2@
Taille espérée d’échantillon
n
*
= 100
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqipu0Je9sqqrpepC0xbbL8F4rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbeqabeWacmGabiqabeqabmqabeabbaGcbaGaamOBamaaCa
aaleqabaGaaGOkaaaakiaai2dacaaIXaGaaGimaiaaicdaaaa@39CC@
Sommaire du tableau
Le tableau montre les résultats de Tableau 5.2
Populations artificielles (taille de population BIAIS et REQM des estimateurs de la fonction de répartition sous échantillonnage de Poisson avec probabilités d’inclusion dans l’échantillon proportionnelles aux écarts-types des lois de Student non centrales avec dl et avec paramètres de non-centralité Taille espérée d’échantillon
XXXX , XXXX, BIAIS , REQM et REQM , calculées selon XXXX avec XXXX i.i.d. de Student centrale XXXX avec XXXX, XXXX avec XXXX indép. de Student non centrale XXXX avec XXXX et XXXX, XXXX avec XXXX i.i.d. de Student XXXX avec XXXX, XXXX avec XXXX indép. de Student non centrale XXXX avec XXXX et XXXX, XXXX avec XXXX i.i.d. de Student XXXX avec XXXX et XXXX avec XXXX indép. de Student non centrale XXXX avec XXXX et XXXX unités de mesure (figurant comme en-tête de colonne).
t =
F
N
− 1
(
0,05
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbeqabeWacmGabiqabeqabmqabeabbaGcbaGaamiDaiaai2
dacaWGgbWaa0baaSqaaiaad6eaaeaacqGHsislcaaIXaaaaOWaaeWa
aeaacaaIWaGaaGOlaiaaicdacaaI1aaacaGLOaGaayzkaaaaaa@40DB@
t =
F
N
− 1
(
0,25
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbeqabeWacmGabiqabeqabmqabeabbaGcbaGaamiDaiaai2
dacaWGgbWaa0baaSqaaiaad6eaaeaacqGHsislcaaIXaaaaOWaaeWa
aeaacaaIWaGaaGOlaiaaikdacaaI1aaacaGLOaGaayzkaaaaaa@40DD@
t =
F
N
− 1
(
0,50
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbeqabeWacmGabiqabeqabmqabeabbaGcbaGaamiDaiaai2
dacaWGgbWaa0baaSqaaiaad6eaaeaacqGHsislcaaIXaaaaOWaaeWa
aeaacaaIWaGaaGOlaiaaiwdacaaIWaaacaGLOaGaayzkaaaaaa@40DB@
t =
F
N
− 1
(
0,75
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbeqabeWacmGabiqabeqabmqabeabbaGcbaGaamiDaiaai2
dacaWGgbWaa0baaSqaaiaad6eaaeaacqGHsislcaaIXaaaaOWaaeWa
aeaacaaIWaGaaGOlaiaaiEdacaaI1aaacaGLOaGaayzkaaaaaa@40E2@
t =
F
N
− 1
(
0,95
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbeqabeWacmGabiqabeqabmqabeabbaGcbaGaamiDaiaai2
dacaWGgbWaa0baaSqaaiaad6eaaeaacqGHsislcaaIXaaaaOWaaeWa
aeaacaaIWaGaaGOlaiaaiMdacaaI1aaacaGLOaGaayzkaaaaaa@40E4@
BIAIS
REQM
BIAIS
REQM
BIAIS
REQM
BIAIS
REQM
BIAIS
REQM
y
i
=
ε
i
,
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaamyEamaaBa
aaleaacaWGPbaabeaakiaai2dacqaH1oqzdaWgaaWcbaGaamyAaaqa
baGccaGGSaaaaa@3D84@
avec
ε
i
∼
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaeqyTdu2aaS
baaSqaaiaadMgaaeqaaOGaeSipIOdaaa@3B14@
i.i.d.
t
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaamiDaaaa@3819@
de Student centrale avec
ν = 5
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaeqyVd4MaaG
ypaiaaiwdaaaa@3A5E@
F
^
s
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaja
WaaSbaaSqaaiaadohaaeqaaOWaaeWaaeaacaWG0baacaGLOaGaayzk
aaaaaa@3BAB@
-10
252
-11
593
-22
738
-20
743
6
357
F
^
l
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaja
WaaSbaaSqaaiaadYgaaeqaaOWaaeWaaeaacaWG0baacaGLOaGaayzk
aaaaaa@3BA4@
-1
237
9
543
-15
621
-5
590
11
302
F
^
s
*
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaja
Waa0baaSqaaiaadohaaeaacaaIQaaaaOWaaeWaaeaacaWG0baacaGL
OaGaayzkaaaaaa@3C60@
22
244
-29
485
-3
555
9
515
-17
297
F
^
l
*
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaja
Waa0baaSqaaiaadYgaaeaacaaIQaaaaOWaaeWaaeaacaWG0baacaGL
OaGaayzkaaaaaa@3C59@
14
238
-10
492
-5
564
14
524
-1
283
F
˜
s
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaia
WaaSbaaSqaaiaadohaaeqaaOWaaeWaaeaacaWG0baacaGLOaGaayzk
aaaaaa@3BAA@
-6
247
0
579
-27
724
-40
736
3
349
F
˜
l
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaia
WaaSbaaSqaaiaadYgaaeqaaOWaaeWaaeaacaWG0baacaGLOaGaayzk
aaaaaa@3BA3@
-2
231
11
526
-1
598
-10
566
7
285
F
˜
s
*
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaia
Waa0baaSqaaiaadohaaeaacaaIQaaaaOWaaeWaaeaacaWG0baacaGL
OaGaayzkaaaaaa@3C5F@
23
248
23
505
-4
562
-27
531
-20
304
F
˜
l
*
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaia
Waa0baaSqaaiaadYgaaeaacaaIQaaaaOWaaeWaaeaacaWG0baacaGL
OaGaayzkaaaaaa@3C58@
12
240
20
504
1
573
-13
538
-6
287
F
˜
π
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaia
WaaSbaaSqaaiabec8aWbqabaGcdaqadaqaaiaadshaaiaawIcacaGL
Paaaaaa@3C6F@
-6
220
-7
543
-37
741
-44
929
-48
1 058
y
i
=
ε
i
,
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaamyEamaaBa
aaleaacaWGPbaabeaakiaai2dacqaH1oqzdaWgaaWcbaGaamyAaaqa
baGccaGGSaaaaa@3D84@
avec
ε
i
∼
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaeqyTdu2aaS
baaSqaaiaadMgaaeqaaOGaeSipIOdaaa@3B14@
indép.
t
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaamiDaaaa@3819@
de Student non centrale avec
ν = 5
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaeqyVd4MaaG
ypaiaaiwdaaaa@3A5E@
et
μ = 15
x
i
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaeqiVd0MaaG
ypaiaaigdacaaI1aGaamiEamaaBaaaleaacaWGPbaabeaaaaa@3D2E@
F
^
s
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaja
WaaSbaaSqaaiaadohaaeqaaOWaaeWaaeaacaWG0baacaGLOaGaayzk
aaaaaa@3BAB@
17
164
30
411
4
749
14
590
15
190
F
^
l
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaja
WaaSbaaSqaaiaadYgaaeqaaOWaaeWaaeaacaWG0baacaGLOaGaayzk
aaaaaa@3BA4@
47
173
19
383
-1
602
57
498
15
187
F
^
s
*
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaja
Waa0baaSqaaiaadohaaeaacaaIQaaaaOWaaeWaaeaacaWG0baacaGL
OaGaayzkaaaaaa@3C60@
21
175
-7
378
-89
554
-11
473
3
192
F
^
l
*
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaja
Waa0baaSqaaiaadYgaaeaacaaIQaaaaOWaaeWaaeaacaWG0baacaGL
OaGaayzkaaaaaa@3C59@
29
152
-3
367
-99
555
27
481
3
184
F
˜
s
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaia
WaaSbaaSqaaiaadohaaeqaaOWaaeWaaeaacaWG0baacaGLOaGaayzk
aaaaaa@3BAA@
1
159
10
406
-11
737
-5
579
-2
194
F
˜
l
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaia
WaaSbaaSqaaiaadYgaaeqaaOWaaeWaaeaacaWG0baacaGLOaGaayzk
aaaaaa@3BA3@
1
158
9
388
-5
586
14
482
-1
192
F
˜
s
*
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaia
Waa0baaSqaaiaadohaaeaacaaIQaaaaOWaaeWaaeaacaWG0baacaGL
OaGaayzkaaaaaa@3C5F@
14
186
27
409
-3
562
-17
487
-10
200
F
˜
l
*
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaia
Waa0baaSqaaiaadYgaaeaacaaIQaaaaOWaaeWaaeaacaWG0baacaGL
OaGaayzkaaaaaa@3C58@
3
160
22
399
-11
566
-5
482
-2
193
F
˜
π
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaia
WaaSbaaSqaaiabec8aWbqabaGcdaqadaqaaiaadshaaiaawIcacaGL
Paaaaaa@3C6F@
-3
162
-7
451
-31
738
-29
980
-55
1 067
y
i
= 10
x
i
+
ε
i
,
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaamyEamaaBa
aaleaacaWGPbaabeaakiaai2dacaaIXaGaaGimaiaadIhadaWgaaWc
baGaamyAaaqabaGccqGHRaWkcqaH1oqzdaWgaaWcbaGaamyAaaqaba
GccaGGSaaaaa@41FC@
avec
ε
i
∼
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaeqyTdu2aaS
baaSqaaiaadMgaaeqaaOGaeSipIOdaaa@3B14@
i.i.d.
t
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaamiDaaaa@3819@
de Student centrale avec
ν = 5
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaeqyVd4MaaG
ypaiaaiwdaaaa@3A5E@
F
^
s
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaja
WaaSbaaSqaaiaadohaaeqaaOWaaeWaaeaacaWG0baacaGLOaGaayzk
aaaaaa@3BAB@
8
461
21
561
-12
259
-18
218
-30
164
F
^
l
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaja
WaaSbaaSqaaiaadYgaaeqaaOWaaeWaaeaacaWG0baacaGLOaGaayzk
aaaaaa@3BA4@
78
429
183
451
2
248
-161
261
-79
189
F
^
s
*
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaja
Waa0baaSqaaiaadohaaeaacaaIQaaaaOWaaeWaaeaacaWG0baacaGL
OaGaayzkaaaaaa@3C60@
-69
306
12
340
10
267
15
199
6
143
F
^
l
*
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaja
Waa0baaSqaaiaadYgaaeaacaaIQaaaaOWaaeWaaeaacaWG0baacaGL
OaGaayzkaaaaaa@3C59@
-59
294
4
302
56
205
15
172
17
124
F
˜
s
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaia
WaaSbaaSqaaiaadohaaeqaaOWaaeWaaeaacaWG0baacaGLOaGaayzk
aaaaaa@3BAA@
-25
441
4
560
-10
257
9
219
5
153
F
˜
l
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaia
WaaSbaaSqaaiaadYgaaeqaaOWaaeWaaeaacaWG0baacaGLOaGaayzk
aaaaaa@3BA3@
-14
372
35
410
-10
262
4
219
5
151
F
˜
s
*
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaia
Waa0baaSqaaiaadohaaeaacaaIQaaaaOWaaeWaaeaacaWG0baacaGL
OaGaayzkaaaaaa@3C5F@
-31
333
-2
386
-29
294
4
227
-1
161
F
˜
l
*
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaia
Waa0baaSqaaiaadYgaaeaacaaIQaaaaOWaaeWaaeaacaWG0baacaGL
OaGaayzkaaaaaa@3C58@
-20
339
15
372
-10
259
11
215
4
151
F
˜
π
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaia
WaaSbaaSqaaiabec8aWbqabaGcdaqadaqaaiaadshaaiaawIcacaGL
Paaaaaa@3C6F@
-15
385
3
746
-37
917
-35
1 004
-48
1 070
y
i
= 10
x
i
+
ε
i
,
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaamyEamaaBa
aaleaacaWGPbaabeaakiaai2dacaaIXaGaaGimaiaadIhadaWgaaWc
baGaamyAaaqabaGccqGHRaWkcqaH1oqzdaWgaaWcbaGaamyAaaqaba
GccaGGSaaaaa@41FC@
avec
ε
i
∼
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaeqyTdu2aaS
baaSqaaiaadMgaaeqaaOGaeSipIOdaaa@3B14@
indép.
t
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaamiDaaaa@3819@
de Student non centrale avec
ν = 5
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaeqyVd4MaaG
ypaiaaiwdaaaa@3A5E@
et
μ = 15
x
i
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaeqiVd0MaaG
ypaiaaigdacaaI1aGaamiEamaaBaaaleaacaWGPbaabeaaaaa@3D2E@
F
^
s
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaja
WaaSbaaSqaaiaadohaaeqaaOWaaeWaaeaacaWG0baacaGLOaGaayzk
aaaaaa@3BAB@
-4
516
30
671
7
453
11
344
6
182
F
^
l
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaja
WaaSbaaSqaaiaadYgaaeqaaOWaaeWaaeaacaWG0baacaGLOaGaayzk
aaaaaa@3BA4@
63
409
129
539
61
421
9
341
1
180
F
^
s
*
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaja
Waa0baaSqaaiaadohaaeaacaaIQaaaaOWaaeWaaeaacaWG0baacaGL
OaGaayzkaaaaaa@3C60@
44
300
-29
433
-45
422
-47
345
12
180
F
^
l
*
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaja
Waa0baaSqaaiaadYgaaeaacaaIQaaaaOWaaeWaaeaacaWG0baacaGL
OaGaayzkaaaaaa@3C59@
107
314
-41
420
-60
397
-22
323
31
171
F
˜
s
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaia
WaaSbaaSqaaiaadohaaeqaaOWaaeWaaeaacaWG0baacaGLOaGaayzk
aaaaaa@3BAA@
-27
502
8
667
-8
450
0
344
-8
185
F
˜
l
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaia
WaaSbaaSqaaiaadYgaaeqaaOWaaeWaaeaacaWG0baacaGLOaGaayzk
aaaaaa@3BA3@
-10
364
16
510
11
425
-2
345
-7
182
F
˜
s
*
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaia
Waa0baaSqaaiaadohaaeaacaaIQaaaaOWaaeWaaeaacaWG0baacaGL
OaGaayzkaaaaaa@3C5F@
-6
325
-9
479
-25
447
-14
356
-10
187
F
˜
l
*
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaia
Waa0baaSqaaiaadYgaaeaacaaIQaaaaOWaaeWaaeaacaWG0baacaGL
OaGaayzkaaaaaa@3C58@
-7
332
-9
489
-5
426
-3
344
-6
182
F
˜
π
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaia
WaaSbaaSqaaiabec8aWbqabaGcdaqadaqaaiaadshaaiaawIcacaGL
Paaaaaa@3C6F@
-16
349
-2
705
-21
886
-42
1 013
-61
1 069
y
i
= 10
x
i
1 / 4
+
ε
i
,
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaamyEamaaBa
aaleaacaWGPbaabeaakiaai2dacaaIXaGaaGimaiaadIhadaqhaaWc
baGaamyAaaqaamaalyaabaGaaGymaaqaaiaaisdaaaaaaOGaey4kaS
IaeqyTdu2aaSbaaSqaaiaadMgaaeqaaOGaaiilaaaa@438C@
avec
ε
i
∼
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaeqyTdu2aaS
baaSqaaiaadMgaaeqaaOGaeSipIOdaaa@3B14@
i.i.d.
t
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaamiDaaaa@3819@
de Student avec
ν = 5
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaeqyVd4MaaG
ypaiaaiwdaaaa@3A5E@
F
^
s
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaja
WaaSbaaSqaaiaadohaaeqaaOWaaeWaaeaacaWG0baacaGLOaGaayzk
aaaaaa@3BAB@
36
497
47
629
9
418
-11
320
15
191
F
^
l
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaja
WaaSbaaSqaaiaadYgaaeqaaOWaaeWaaeaacaWG0baacaGLOaGaayzk
aaaaaa@3BA4@
56
393
186
490
43
383
-48
308
13
184
F
^
s
*
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaja
Waa0baaSqaaiaadohaaeaacaaIQaaaaOWaaeWaaeaacaWG0baacaGL
OaGaayzkaaaaaa@3C60@
-29
276
-19
383
-18
380
-43
335
-1
204
F
^
l
*
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaja
Waa0baaSqaaiaadYgaaeaacaaIQaaaaOWaaeWaaeaacaWG0baacaGL
OaGaayzkaaaaaa@3C59@
-29
274
10
355
7
336
-29
290
23
179
F
˜
s
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaia
WaaSbaaSqaaiaadohaaeqaaOWaaeWaaeaacaWG0baacaGLOaGaayzk
aaaaaa@3BAA@
-30
475
12
630
4
421
7
317
6
191
F
˜
l
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaia
WaaSbaaSqaaiaadYgaaeqaaOWaaeWaaeaacaWG0baacaGLOaGaayzk
aaaaaa@3BA3@
-42
336
31
452
11
390
8
312
8
186
F
˜
s
*
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaia
Waa0baaSqaaiaadohaaeaacaaIQaaaaOWaaeWaaeaacaWG0baacaGL
OaGaayzkaaaaaa@3C5F@
-31
306
5
429
-18
406
-14
344
-8
210
F
˜
l
*
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaia
Waa0baaSqaaiaadYgaaeaacaaIQaaaaOWaaeWaaeaacaWG0baacaGL
OaGaayzkaaaaaa@3C58@
-28
308
14
424
7
387
5
315
7
191
F
˜
π
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaia
WaaSbaaSqaaiabec8aWbqabaGcdaqadaqaaiaadshaaiaawIcacaGL
Paaaaaa@3C6F@
-15
380
10
739
-23
891
-37
993
-47
1 064
y
i
= 10
x
i
1 / 4
+
ε
i
,
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaamyEamaaBa
aaleaacaWGPbaabeaakiaai2dacaaIXaGaaGimaiaadIhadaqhaaWc
baGaamyAaaqaamaalyaabaGaaGymaaqaaiaaisdaaaaaaOGaey4kaS
IaeqyTdu2aaSbaaSqaaiaadMgaaeqaaOGaaiilaaaa@438C@
avec
ε
i
∼
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaeqyTdu2aaS
baaSqaaiaadMgaaeqaaOGaeSipIOdaaa@3B14@
indép.
t
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaamiDaaaa@3819@
de Student non centrale avec
ν = 5
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaeqyVd4MaaG
ypaiaaiwdaaaa@3A5E@
et
μ = 15
x
i
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaeqiVd0MaaG
ypaiaaigdacaaI1aGaamiEamaaBaaaleaacaWGPbaabeaaaaa@3D2E@
F
^
s
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaja
WaaSbaaSqaaiaadohaaeqaaOWaaeWaaeaacaWG0baacaGLOaGaayzk
aaaaaa@3BAB@
24
308
69
687
53
690
38
406
2
188
F
^
l
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaja
WaaSbaaSqaaiaadYgaaeqaaOWaaeWaaeaacaWG0baacaGLOaGaayzk
aaaaaa@3BA4@
47
301
131
553
139
561
91
393
-2
186
F
^
s
*
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaja
Waa0baaSqaaiaadohaaeaacaaIQaaaaOWaaeWaaeaacaWG0baacaGL
OaGaayzkaaaaaa@3C60@
15
237
2
435
-135
513
-59
411
12
186
F
^
l
*
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaja
Waa0baaSqaaiaadYgaaeaacaaIQaaaaOWaaeWaaeaacaWG0baacaGL
OaGaayzkaaaaaa@3C59@
27
235
18
435
-149
506
-5
374
13
179
F
˜
s
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaia
WaaSbaaSqaaiaadohaaeqaaOWaaeWaaeaacaWG0baacaGLOaGaayzk
aaaaaa@3BAA@
-28
274
-8
673
4
688
3
403
-10
191
F
˜
l
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaia
WaaSbaaSqaaiaadYgaaeqaaOWaaeWaaeaacaWG0baacaGLOaGaayzk
aaaaaa@3BA3@
-29
251
-12
512
17
541
7
395
-9
188
F
˜
s
*
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaia
Waa0baaSqaaiaadohaaeaacaaIQaaaaOWaaeWaaeaacaWG0baacaGL
OaGaayzkaaaaaa@3C5F@
-3
255
-12
481
-7
536
-20
422
-12
196
F
˜
l
*
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaia
Waa0baaSqaaiaadYgaaeaacaaIQaaaaOWaaeWaaeaacaWG0baacaGL
OaGaayzkaaaaaa@3C58@
-12
251
-16
489
2
538
-4
399
-9
189
F
˜
π
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaia
WaaSbaaSqaaiabec8aWbqabaGcdaqadaqaaiaadshaaiaawIcacaGL
Paaaaaa@3C6F@
-10
267
-8
608
-4
860
-38
1 009
-63
1 066
Tableau 5.3
Populations réelles (taille de population
N = 284 ) .
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqipu0Je9sqqrpepC0xbbL8F4rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbeqabeWacmGabiqabeqabmqabeabbaGcbaWaaeGaaeaaca
WGobGaaGypaiaaikdacaaI4aGaaGinaaGaayzkaaGaaiOlaaaa@3A48@
BIAIS et REQM des estimateurs de la fonction de répartition sous échantillonnage aléatoire simple sans remise. Taille d’échantillon
n = 30
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqipu0Je9sqqrpepC0xbbL8F4rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbeqabeWacmGabiqabeqabmqabeabbaGcbaGaamOBaiaai2
dacaaIZaGaaGimaaaa@3829@
Sommaire du tableau
Le tableau montre les résultats de Tableau 5.3
Populations réelles (taille de population XXXX BIAIS et REQM des estimateurs de la fonction de répartition sous échantillonnage aléatoire simple sans remise. Taille d’échantillon XXXX
BIAIS , REQM , REQM and BIAISR , MU284 Population avec XXXX et XXXX unités de mesure (figurant comme en-tête de colonne).
t =
F
N
− 1
(
0,05
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbeqabeWacmGabiqabeqabmqabeabbaGcbaGaamiDaiaai2
dacaWGgbWaa0baaSqaaiaad6eaaeaacqGHsislcaaIXaaaaOWaaeWa
aeaacaaIWaGaaGOlaiaaicdacaaI1aaacaGLOaGaayzkaaaaaa@40DB@
t =
F
N
− 1
(
0,25
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbeqabeWacmGabiqabeqabmqabeabbaGcbaGaamiDaiaai2
dacaWGgbWaa0baaSqaaiaad6eaaeaacqGHsislcaaIXaaaaOWaaeWa
aeaacaaIWaGaaGOlaiaaikdacaaI1aaacaGLOaGaayzkaaaaaa@40DD@
t =
F
N
− 1
(
0,50
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbeqabeWacmGabiqabeqabmqabeabbaGcbaGaamiDaiaai2
dacaWGgbWaa0baaSqaaiaad6eaaeaacqGHsislcaaIXaaaaOWaaeWa
aeaacaaIWaGaaGOlaiaaiwdacaaIWaaacaGLOaGaayzkaaaaaa@40DB@
t =
F
N
− 1
(
0,75
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbeqabeWacmGabiqabeqabmqabeabbaGcbaGaamiDaiaai2
dacaWGgbWaa0baaSqaaiaad6eaaeaacqGHsislcaaIXaaaaOWaaeWa
aeaacaaIWaGaaGOlaiaaiEdacaaI1aaacaGLOaGaayzkaaaaaa@40E2@
t =
F
N
− 1
(
0,95
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbeqabeWacmGabiqabeqabmqabeabbaGcbaGaamiDaiaai2
dacaWGgbWaa0baaSqaaiaad6eaaeaacqGHsislcaaIXaaaaOWaaeWa
aeaacaaIWaGaaGOlaiaaiMdacaaI1aaacaGLOaGaayzkaaaaaa@40E4@
BIAIS
REQM
BIAIS
REQM
BIAISR
REQM
BIAIS
REQM
BIAIS
REQM
Population MU284 avec
Y = ln R M T 85
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaamywaiaai2
daciGGSbGaaiOBaiaadkfacaWGnbGaamivaiaaiIdacaaI1aaaaa@3EAC@
et
X = ln P 85
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaamiwaiaai2
daciGGSbGaaiOBaiaadcfacaaI4aGaaGynaaaa@3CFE@
F
^
s
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaja
WaaSbaaSqaaiaadohaaeqaaOWaaeWaaeaacaWG0baacaGLOaGaayzk
aaaaaa@3BAB@
133
421
339
625
180
529
-265
490
-187
439
F
^
l
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaja
WaaSbaaSqaaiaadYgaaeqaaOWaaeWaaeaacaWG0baacaGLOaGaayzk
aaaaaa@3BA4@
52
380
67
588
45
555
-63
469
-87
370
F
^
s
*
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaja
Waa0baaSqaaiaadohaaeaacaaIQaaaaOWaaeWaaeaacaWG0baacaGL
OaGaayzkaaaaaa@3C60@
8
81
-154
203
90
130
62
123
6
54
F
^
l
*
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaja
Waa0baaSqaaiaadYgaaeaacaaIQaaaaOWaaeWaaeaacaWG0baacaGL
OaGaayzkaaaaaa@3C59@
28
66
-170
212
69
112
57
109
2
50
F
˜
s
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaia
WaaSbaaSqaaiaadohaaeqaaOWaaeWaaeaacaWG0baacaGLOaGaayzk
aaaaaa@3BAA@
-28
300
-24
497
8
483
-48
421
-38
319
F
˜
l
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaia
WaaSbaaSqaaiaadYgaaeqaaOWaaeWaaeaacaWG0baacaGLOaGaayzk
aaaaaa@3BA3@
-28
326
-96
569
-52
544
3
466
1
319
F
˜
s
*
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaia
Waa0baaSqaaiaadohaaeaacaaIQaaaaOWaaeWaaeaacaWG0baacaGL
OaGaayzkaaaaaa@3C5F@
26
177
-11
302
0
244
1
308
-18
102
F
˜
l
*
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaia
Waa0baaSqaaiaadYgaaeaacaaIQaaaaOWaaeWaaeaacaWG0baacaGL
OaGaayzkaaaaaa@3C58@
29
179
-10
302
-2
243
-1
308
-21
104
F
˜
π
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaia
WaaSbaaSqaaiabec8aWbqabaGcdaqadaqaaiaadshaaiaawIcacaGL
Paaaaaa@3C6F@
22
388
-10
771
9
864
5
731
-43
394
Population MU284 avec
Y = ln R M T 85
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaamywaiaai2
daciGGSbGaaiOBaiaadkfacaWGnbGaamivaiaaiIdacaaI1aaaaa@3EAC@
et
X = ln R E V 84
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaamiwaiaai2
daciGGSbGaaiOBaiaadkfacaWGfbGaamOvaiaaiIdacaaI0aaaaa@3EA4@
F
^
s
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaja
WaaSbaaSqaaiaadohaaeqaaOWaaeWaaeaacaWG0baacaGLOaGaayzk
aaaaaa@3BAB@
143
449
303
643
138
554
-217
543
-166
446
F
^
l
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaja
WaaSbaaSqaaiaadYgaaeqaaOWaaeWaaeaacaWG0baacaGLOaGaayzk
aaaaaa@3BA4@
62
395
62
611
36
582
-49
519
-71
376
F
^
s
*
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaja
Waa0baaSqaaiaadohaaeaacaaIQaaaaOWaaeWaaeaacaWG0baacaGL
OaGaayzkaaaaaa@3C60@
-11
204
-32
300
-101
328
42
285
31
155
F
^
l
*
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaja
Waa0baaSqaaiaadYgaaeaacaaIQaaaaOWaaeWaaeaacaWG0baacaGL
OaGaayzkaaaaaa@3C59@
36
183
-40
288
-149
345
6
261
34
122
F
˜
s
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaia
WaaSbaaSqaaiaadohaaeqaaOWaaeWaaeaacaWG0baacaGLOaGaayzk
aaaaaa@3BAA@
5
340
-22
548
4
557
-30
498
-23
332
F
˜
l
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaia
WaaSbaaSqaaiaadYgaaeqaaOWaaeWaaeaacaWG0baacaGLOaGaayzk
aaaaaa@3BA3@
-2
349
-78
599
-36
588
10
522
8
331
F
˜
s
*
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaia
Waa0baaSqaaiaadohaaeaacaaIQaaaaOWaaeWaaeaacaWG0baacaGL
OaGaayzkaaaaaa@3C5F@
24
303
7
446
-6
494
2
439
-13
209
F
˜
l
*
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaia
Waa0baaSqaaiaadYgaaeaacaaIQaaaaOWaaeWaaeaacaWG0baacaGL
OaGaayzkaaaaaa@3C58@
29
304
4
443
-6
495
-1
432
-18
192
F
˜
π
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaia
WaaSbaaSqaaiabec8aWbqabaGcdaqadaqaaiaadshaaiaawIcacaGL
Paaaaaa@3C6F@
34
395
1
766
16
880
9
744
-37
398
Tableau 5.4
Populations réelles (taille de population
N = 284 ) .
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqipu0Je9sqqrpepC0xbbL8F4rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbeqabeWacmGabiqabeqabmqabeabbaGcbaWaaeGaaeaaca
WGobGaaGypaiaaikdacaaI4aGaaGinaaGaayzkaaGaaiOlaaaa@3A48@
BIAIS et REQM des estimateurs de la fonction de répartition sous échantillonnage de Poisson avec probabilités d’inclusion proportionnelles à la valeur absolue des résidus de la régression linéaire des valeurs
y
i
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqipu0Je9sqqrpepC0xbbL8F4rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbeqabeWacmGabiqabeqabmqabeabbaGcbaGaamyEamaaBa
aaleaacaWGPbaabeaakiabgkHiTaaa@3807@
de la population sur les valeurs
x
i
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqipu0Je9sqqrpepC0xbbL8F4rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbeqabeWacmGabiqabeqabmqabeabbaGcbaGaamiEamaaBa
aaleaacaWGPbaabeaakiabgkHiTaaa@3806@
de la population. Taille espérée
n
*
= 30
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqipu0Je9sqqrpepC0xbbL8F4rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbeqabeWacmGabiqabeqabmqabeabbaGcbaGaamOBamaaCa
aaleqabaGaaGOkaaaakiaai2dacaaIZaGaaGimaaaa@3914@
Sommaire du tableau
Le tableau montre les résultats de Populations réelles (taille de population XXXX BIAIS et REQM des estimateurs de la fonction de répartition sous échantillonnage de Poisson avec probabilités d’inclusion proportionnelles à la valeur absolue des résidus de la régression linéaire des valeurs XXXX de la population sur les valeurs XXXX de la population. Taille espérée XXXX XXXX, BIAIS , REQM , REQM et BIAISR , calculées selon Population MU284 avec XXXX et XXXX unités de mesure (figurant comme en-tête de colonne).
t =
F
N
− 1
(
0,05
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbeqabeWacmGabiqabeqabmqabeabbaGcbaGaamiDaiaai2
dacaWGgbWaa0baaSqaaiaad6eaaeaacqGHsislcaaIXaaaaOWaaeWa
aeaacaaIWaGaaGOlaiaaicdacaaI1aaacaGLOaGaayzkaaaaaa@40DB@
t =
F
N
− 1
(
0,25
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbeqabeWacmGabiqabeqabmqabeabbaGcbaGaamiDaiaai2
dacaWGgbWaa0baaSqaaiaad6eaaeaacqGHsislcaaIXaaaaOWaaeWa
aeaacaaIWaGaaGOlaiaaikdacaaI1aaacaGLOaGaayzkaaaaaa@40DD@
t =
F
N
− 1
(
0,50
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbeqabeWacmGabiqabeqabmqabeabbaGcbaGaamiDaiaai2
dacaWGgbWaa0baaSqaaiaad6eaaeaacqGHsislcaaIXaaaaOWaaeWa
aeaacaaIWaGaaGOlaiaaiwdacaaIWaaacaGLOaGaayzkaaaaaa@40DB@
t =
F
N
− 1
(
0,75
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbeqabeWacmGabiqabeqabmqabeabbaGcbaGaamiDaiaai2
dacaWGgbWaa0baaSqaaiaad6eaaeaacqGHsislcaaIXaaaaOWaaeWa
aeaacaaIWaGaaGOlaiaaiEdacaaI1aaacaGLOaGaayzkaaaaaa@40E2@
t =
F
N
− 1
(
0,95
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbeqabeWacmGabiqabeqabmqabeabbaGcbaGaamiDaiaai2
dacaWGgbWaa0baaSqaaiaad6eaaeaacqGHsislcaaIXaaaaOWaaeWa
aeaacaaIWaGaaGOlaiaaiMdacaaI1aaacaGLOaGaayzkaaaaaa@40E4@
BIAIS
REQM
BIAIS
REQM
BIAISR
REQM
BIAIS
REQM
BIAIS
REQM
Population MU284 avec
Y = ln R M T 85
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaamywaiaai2
daciGGSbGaaiOBaiaadkfacaWGnbGaamivaiaaiIdacaaI1aaaaa@3EAC@
et
X = ln P 85
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaamiwaiaai2
daciGGSbGaaiOBaiaadcfacaaI4aGaaGynaaaa@3CFE@
F
^
s
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaja
WaaSbaaSqaaiaadohaaeqaaOWaaeWaaeaacaWG0baacaGLOaGaayzk
aaaaaa@3BAB@
204
420
485
668
239
519
-412
626
-90
317
F
^
l
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaja
WaaSbaaSqaaiaadYgaaeqaaOWaaeWaaeaacaWG0baacaGLOaGaayzk
aaaaaa@3BA4@
180
424
417
684
319
614
-239
548
-148
348
F
^
s
*
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaja
Waa0baaSqaaiaadohaaeaacaaIQaaaaOWaaeWaaeaacaWG0baacaGL
OaGaayzkaaaaaa@3C60@
-41
97
-118
199
132
178
40
140
-71
104
F
^
l
*
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaja
Waa0baaSqaaiaadYgaaeaacaaIQaaaaOWaaeWaaeaacaWG0baacaGL
OaGaayzkaaaaaa@3C59@
11
70
-147
211
63
128
-25
122
-85
106
F
˜
s
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaia
WaaSbaaSqaaiaadohaaeqaaOWaaeWaaeaacaWG0baacaGLOaGaayzk
aaaaaa@3BAA@
24
360
30
649
0
675
-68
614
58
368
F
˜
l
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaia
WaaSbaaSqaaiaadYgaaeqaaOWaaeWaaeaacaWG0baacaGLOaGaayzk
aaaaaa@3BA3@
9
390
-63
737
-64
774
-7
682
75
414
F
˜
s
*
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaia
Waa0baaSqaaiaadohaaeaacaaIQaaaaOWaaeWaaeaacaWG0baacaGL
OaGaayzkaaaaaa@3C5F@
16
184
-14
307
36
283
16
323
-11
103
F
˜
l
*
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaia
Waa0baaSqaaiaadYgaaeaacaaIQaaaaOWaaeWaaeaacaWG0baacaGL
OaGaayzkaaaaaa@3C58@
25
187
-15
312
30
286
14
328
-11
112
F
˜
π
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaia
WaaSbaaSqaaiabec8aWbqabaGcdaqadaqaaiaadshaaiaawIcacaGL
Paaaaaa@3C6F@
40
445
73
1 983
12
2 498
-43
3 094
-49
3 341
Population MU284 avec
Y = ln R M T 85
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaamywaiaai2
daciGGSbGaaiOBaiaadkfacaWGnbGaamivaiaaiIdacaaI1aaaaa@3EAC@
et
X = ln R E V 84
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaamiwaiaai2
daciGGSbGaaiOBaiaadkfacaWGfbGaamOvaiaaiIdacaaI0aaaaa@3EA4@
F
^
s
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaja
WaaSbaaSqaaiaadohaaeqaaOWaaeWaaeaacaWG0baacaGLOaGaayzk
aaaaaa@3BAB@
349
660
1 185
1 373
890
1 059
458
654
-32
270
F
^
l
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaja
WaaSbaaSqaaiaadYgaaeqaaOWaaeWaaeaacaWG0baacaGLOaGaayzk
aaaaaa@3BA4@
287
601
1 003
1 236
771
989
484
695
42
263
F
^
s
*
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaja
Waa0baaSqaaiaadohaaeaacaaIQaaaaOWaaeWaaeaacaWG0baacaGL
OaGaayzkaaaaaa@3C60@
317
453
739
866
761
879
624
701
159
207
F
^
l
*
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaja
Waa0baaSqaaiaadYgaaeaacaaIQaaaaOWaaeWaaeaacaWG0baacaGL
OaGaayzkaaaaaa@3C59@
364
471
720
842
718
824
572
647
96
158
F
˜
s
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaia
WaaSbaaSqaaiaadohaaeqaaOWaaeWaaeaacaWG0baacaGLOaGaayzk
aaaaaa@3BAA@
35
488
82
818
-31
772
7
634
-8
326
F
˜
l
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaia
WaaSbaaSqaaiaadYgaaeqaaOWaaeWaaeaacaWG0baacaGLOaGaayzk
aaaaaa@3BA3@
22
500
3
878
-98
852
40
704
27
354
F
˜
s
*
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaia
Waa0baaSqaaiaadohaaeaacaaIQaaaaOWaaeWaaeaacaWG0baacaGL
OaGaayzkaaaaaa@3C5F@
37
317
32
498
-13
513
32
412
7
157
F
˜
l
*
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaia
Waa0baaSqaaiaadYgaaeaacaaIQaaaaOWaaeWaaeaacaWG0baacaGL
OaGaayzkaaaaaa@3C58@
51
313
30
498
-30
518
12
411
-10
149
F
˜
π
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOrayaaia
WaaSbaaSqaaiabec8aWbqabaGcdaqadaqaaiaadshaaiaawIcacaGL
Paaaaaa@3C6F@
32
671
19
1 658
-172
2 354
-173
2 787
-191
2 935
Considérons enfin les résultats des simulations concernant les
estimateurs de variance de la section 4. Les tableaux 5.5 à 5.8
donnent le biais relatif (BIAISR) et la racine carrée de l’erreur quadratique
moyenne relative (REQMR) pour chacun d’eux. Par exemple, selon les estimations de
variance
V
˜
b
(
F
˜
(
t
)
) ,
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaaceWGwbGbaG
aadaWgaaWcbaGaamOyaaqabaGcdaqadaqaaiqadAeagaacamaabmaa
baGaamiDaaGaayjkaiaawMcaaaGaayjkaiaawMcaaiaacYcaaaa@3F8D@
b = 1,2,… , B ,
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWGIbGaaG
ypaiaaigdacaaISaGaaGOmaiaaiYcacqWIMaYscaaISaGaamOqaiaa
cYcaaaa@3FD1@
obtenues au moyen de
l’estimateur
V
˜
(
F
˜
(
t
)
) ,
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaaceWGwbGbaG
aadaqadaqaaiqadAeagaacamaabmaabaGaamiDaaGaayjkaiaawMca
aaGaayjkaiaawMcaaiaacYcaaaa@3E70@
BIAISR :=
1
B
∑
b = 1
B
V
˜
b
(
F
˜
(
t
)
) −
V
B
(
F
˜
(
t
)
)
V
B
(
F
˜
(
t
)
)
× 10 000
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaqGcbGaae
ysaiaabgeacaqGjbGaae4uaiaabkfacaaI6aGaaGypamaalaaabaGa
aGymaaqaaiaadkeaaaWaaabCaeqaleaacaWGIbGaaGypaiaaigdaae
aacaWGcbaaniabggHiLdGcdaWcaaqaaiqadAfagaacamaaBaaaleaa
caWGIbaabeaakmaabmaabaGabmOrayaaiaWaaeWaaeaacaWG0baaca
GLOaGaayzkaaaacaGLOaGaayzkaaGaeyOeI0IaamOvamaaBaaaleaa
caWGcbaabeaakmaabmaabaGabmOrayaaiaWaaeWaaeaacaWG0baaca
GLOaGaayzkaaaacaGLOaGaayzkaaaabaGaamOvamaaBaaaleaacaWG
cbaabeaakmaabmaabaGabmOrayaaiaWaaeWaaeaacaWG0baacaGLOa
GaayzkaaaacaGLOaGaayzkaaaaaiabgEna0kaabgdacaqGWaGaaGjb
VlaabcdacaqGWaGaaeimaaaa@61DD@
et
REQMR :=
1
B
∑
b = 1
B
(
V
˜
b
(
F
˜
(
t
)
) −
V
B
(
F
˜
(
t
)
)
)
2
V
B
(
F
˜
(
t
)
)
× 10 000
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaqGsbGaae
yraiaabgfacaqGnbGaaeOuaiaaiQdacaaI9aWaaSaaaeaadaGcaaqa
amaalaaabaGaaGymaaqaaiaadkeaaaWaaabCaeqaleaacaWGIbGaaG
ypaiaaigdaaeaacaWGcbaaniabggHiLdGcdaqadaqaaiqadAfagaac
amaaBaaaleaacaWGIbaabeaakmaabmaabaGabmOrayaaiaWaaeWaae
aacaWG0baacaGLOaGaayzkaaaacaGLOaGaayzkaaGaeyOeI0IaamOv
amaaBaaaleaacaWGcbaabeaakmaabmaabaGabmOrayaaiaWaaeWaae
aacaWG0baacaGLOaGaayzkaaaacaGLOaGaayzkaaaacaGLOaGaayzk
aaWaaWbaaSqabeaacaaIYaaaaaqabaaakeaacaWGwbWaaSbaaSqaai
aadkeaaeqaaOWaaeWaaeaaceWGgbGbaGaadaqadaqaaiaadshaaiaa
wIcacaGLPaaaaiaawIcacaGLPaaaaaGaey41aqRaaeymaiaabcdaca
aMe8UaaeimaiaabcdacaqGWaaaaa@63B3@
où
V
B
(
F
˜
(
t
)
) : =
1
B
∑
b = 1
B
(
F
˜
b
(
t
) −
F
N
(
t
)
)
2
.
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWGwbWaaS
baaSqaaiaadkeaaeqaaOWaaeWaaeaaceWGgbGbaGaadaqadaqaaiaa
dshaaiaawIcacaGLPaaaaiaawIcacaGLPaaacaaI6aGaaGypamaala
aabaGaaGymaaqaaiaadkeaaaWaaabCaeqaleaacaWGIbGaaGypaiaa
igdaaeaacaWGcbaaniabggHiLdGcdaqadaqaaiqadAeagaacamaaBa
aaleaacaWGIbaabeaakmaabmaabaGaamiDaaGaayjkaiaawMcaaiab
gkHiTiaadAeadaWgaaWcbaGaamOtaaqabaGcdaqadaqaaiaadshaai
aawIcacaGLPaaaaiaawIcacaGLPaaadaahaaWcbeqaaiaaikdaaaGc
caaIUaaaaa@5437@
À titre de référence, nous donnons
également les BIAISR et REQMR de l’estimateur
V
˜
(
F
˜
π
(
t
)
) :=
1
N
2
∑
i , j ∈ s
π
i , j
−
π
i
π
j
π
i , j
π
i
π
j
I (
y
i
≤ t
) I (
y
j
≤ t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaaceWGwbGbaG
aadaqadaqaaiqadAeagaacamaaBaaaleaacqaHapaCaeqaaOWaaeWa
aeaacaWG0baacaGLOaGaayzkaaaacaGLOaGaayzkaaGaaGOoaiaai2
dadaWcaaqaaiaaigdaaeaacaWGobWaaWbaaSqabeaacaaIYaaaaaaa
kmaaqafabeWcbaGaamyAaiaaiYcacaWGQbGaeyicI4Saam4Caaqab0
GaeyyeIuoakmaalaaabaGaeqiWda3aaSbaaSqaaiaadMgacaaISaGa
amOAaaqabaGccqGHsislcqaHapaCdaWgaaWcbaGaamyAaaqabaGccq
aHapaCdaWgaaWcbaGaamOAaaqabaaakeaacqaHapaCdaWgaaWcbaGa
amyAaiaaiYcacaWGQbaabeaakiabec8aWnaaBaaaleaacaWGPbaabe
aakiabec8aWnaaBaaaleaacaWGQbaabeaaaaGccaWGjbWaaeWaaeaa
caWG5bWaaSbaaSqaaiaadMgaaeqaaOGaeyizImQaamiDaaGaayjkai
aawMcaaiaadMeadaqadaqaaiaadMhadaWgaaWcbaGaamOAaaqabaGc
cqGHKjYOcaWG0baacaGLOaGaayzkaaaaaa@6EE9@
pour la variance de l’estimateur de
Horvitz-Thompson.
Tableau 5.5
Populations artificielles (taille de population
N
=
1 000
)
.
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqipu0Je9sqqrpepC0xbbL8F4rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbeqabeWacmGabiqabeqabmqabeabbaGcbaWaaeGaaeaaca
WGobGaaGypaiaabgdacaqGSaGaaeimaiaabcdacaqGWaaacaGLPaaa
caGGUaaaaa@3B88@
BIAISR et REQMR des estimateurs de variance sous échantillonnage aléatoire simple sans remise. Taille d’échantillon
n
=
100
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqipu0Je9sqqrpepC0xbbL8F4rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbeqabeWacmGabiqabeqabmqabeabbaGcbaGaamOBaiaai2
dacaaIXaGaaGimaiaaicdaaaa@38E1@
Sommaire du tableau
Le tableau montre les résultats de Populations artificielles (taille de population XXXX BIAISR et REQMR des estimateurs de variance sous échantillonnage aléatoire simple sans remise. Taille d’échantillon XXXX XXXX, BIAISR , REQMR et REQMR , calculées selon avec XXXX i.i.d. XXXX de Student centrale avec XXXX unités de mesure (figurant comme en-tête de colonne).
t
=
F
N
−
1
(
0,05
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbeqabeWacmGabiqabeqabmqabeabbaGcbaGaamiDaiaai2
dacaWGgbWaa0baaSqaaiaad6eaaeaacqGHsislcaaIXaaaaOWaaeWa
aeaacaaIWaGaaGOlaiaaicdacaaI1aaacaGLOaGaayzkaaaaaa@40DB@
t
=
F
N
−
1
(
0,25
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbeqabeWacmGabiqabeqabmqabeabbaGcbaGaamiDaiaai2
dacaWGgbWaa0baaSqaaiaad6eaaeaacqGHsislcaaIXaaaaOWaaeWa
aeaacaaIWaGaaGOlaiaaikdacaaI1aaacaGLOaGaayzkaaaaaa@40DD@
t
=
F
N
−
1
(
0,50
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbeqabeWacmGabiqabeqabmqabeabbaGcbaGaamiDaiaai2
dacaWGgbWaa0baaSqaaiaad6eaaeaacqGHsislcaaIXaaaaOWaaeWa
aeaacaaIWaGaaGOlaiaaiwdacaaIWaaacaGLOaGaayzkaaaaaa@40DB@
t
=
F
N
−
1
(
0,75
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbeqabeWacmGabiqabeqabmqabeabbaGcbaGaamiDaiaai2
dacaWGgbWaa0baaSqaaiaad6eaaeaacqGHsislcaaIXaaaaOWaaeWa
aeaacaaIWaGaaGOlaiaaiEdacaaI1aaacaGLOaGaayzkaaaaaa@40E2@
t
=
F
N
−
1
(
0,95
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbeqabeWacmGabiqabeqabmqabeabbaGcbaGaamiDaiaai2
dacaWGgbWaa0baaSqaaiaad6eaaeaacqGHsislcaaIXaaaaOWaaeWa
aeaacaaIWaGaaGOlaiaaiMdacaaI1aaacaGLOaGaayzkaaaaaa@40E4@
BIAISR
REQMR
BIAISR
REQMR
BIAISR
REQMR
BIAISR
REQMR
BIAISR
REQMR
y
i
=
ε
i
,
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaamyEamaaBa
aaleaacaWGPbaabeaakiaai2dacqaH1oqzdaWgaaWcbaGaamyAaaqa
baGccaGGSaaaaa@3D84@
avec
ε
i
∼
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaeqyTdu2aaS
baaSqaaiaadMgaaeqaaOGaeSipIOdaaa@3B14@
i.i.d.
t
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaamiDaaaa@3819@
de Student centrale avec
ν
=
5
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaeqyVd4MaaG
ypaiaaiwdaaaa@3A5E@
V
˜
(
F
˜
s
(
t
)
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOvayaaia
WaaeWabeaaceWGgbGbaGaadaWgaaWcbaGaam4CaaqabaGcdaqadaqa
aiaadshaaiaawIcacaGLPaaaaiaawIcacaGLPaaaaaa@3E1E@
-1 092
32 442
-1 249
3 895
-1 714
3 077
-1 536
3 828
-824
34 601
V
˜
(
F
˜
l
(
t
)
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOvayaaia
WaaeWabeaaceWGgbGbaGaadaWgaaWcbaGaamiBaaqabaGcdaqadaqa
aiaadshaaiaawIcacaGLPaaaaiaawIcacaGLPaaaaaa@3E17@
-576
31 726
-603
3 838
-1 122
3 374
-951
3 758
-441
33 055
V
˜
(
F
˜
s
*
(
t
)
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOvayaaia
WaaeWabeaaceWGgbGbaGaadaqhaaWcbaGaam4CaaqaaiaaiQcaaaGc
daqadaqaaiaadshaaiaawIcacaGLPaaaaiaawIcacaGLPaaaaaa@3ED3@
-1 091
32 579
-1 292
3 914
-1 708
3 085
-1 640
3 828
-802
34 809
V
˜
(
F
˜
l
*
(
t
)
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOvayaaia
WaaeWabeaaceWGgbGbaGaadaqhaaWcbaGaamiBaaqaaiaaiQcaaaGc
daqadaqaaiaadshaaiaawIcacaGLPaaaaiaawIcacaGLPaaaaaa@3ECC@
-556
31 881
-622
3 857
-1 148
3 361
-1 025
3 749
-425
33 184
V
˜
(
F
˜
π
(
t
)
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOvayaaia
WaaeWabeaaceWGgbGbaGaadaWgaaWcbaGaeqiWdahabeaakmaabmaa
baGaamiDaaGaayjkaiaawMcaaaGaayjkaiaawMcaaaaa@3EE3@
42
30 952
57
3 928
-592
3 776
-287
3 825
551
33 462
y
i
=
ε
i
,
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaamyEamaaBa
aaleaacaWGPbaabeaakiaai2dacqaH1oqzdaWgaaWcbaGaamyAaaqa
baGccaGGSaaaaa@3D84@
avec
ε
i
∼
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaeqyTdu2aaS
baaSqaaiaadMgaaeqaaOGaeSipIOdaaa@3B14@
indép.
t
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaamiDaaaa@3819@
de Student non centrale avec
ν
=
5
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaeqyVd4MaaG
ypaiaaiwdaaaa@3A5E@
et
μ
=
15
x
i
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaeqiVd0MaaG
ypaiaaigdacaaI1aGaamiEamaaBaaaleaacaWGPbaabeaaaaa@3D2E@
V
˜
(
F
˜
s
(
t
)
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOvayaaia
WaaeWabeaaceWGgbGbaGaadaWgaaWcbaGaam4CaaqabaGcdaqadaqa
aiaadshaaiaawIcacaGLPaaaaiaawIcacaGLPaaaaaa@3E1E@
-1 900
29 622
50
4 707
-917
3 557
-998
3 695
-1 480
29 417
V
˜
(
F
˜
l
(
t
)
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOvayaaia
WaaeWabeaaceWGgbGbaGaadaWgaaWcbaGaamiBaaqabaGcdaqadaqa
aiaadshaaiaawIcacaGLPaaaaiaawIcacaGLPaaaaaa@3E17@
-1 359
29 623
535
4 572
-395
3 881
-527
3 736
-1 277
28 267
V
˜
(
F
˜
s
*
(
t
)
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOvayaaia
WaaeWabeaaceWGgbGbaGaadaqhaaWcbaGaam4CaaqaaiaaiQcaaaGc
daqadaqaaiaadshaaiaawIcacaGLPaaaaiaawIcacaGLPaaaaaa@3ED3@
-1 832
30 119
-101
4 710
-991
3 530
-1 077
3 704
-1 398
29 927
V
˜
(
F
˜
l
*
(
t
)
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOvayaaia
WaaeWabeaaceWGgbGbaGaadaqhaaWcbaGaamiBaaqaaiaaiQcaaaGc
daqadaqaaiaadshaaiaawIcacaGLPaaaaiaawIcacaGLPaaaaaa@3ECC@
-1 362
29 713
465
4 559
-420
3 865
-591
3 718
-1 236
28 489
V
˜
(
F
˜
π
(
t
)
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOvayaaia
WaaeWabeaaceWGgbGbaGaadaWgaaWcbaGaeqiWdahabeaakmaabmaa
baGaamiDaaGaayjkaiaawMcaaaGaayjkaiaawMcaaaaa@3EE3@
-351
29 132
1 096
4 215
-78
4 074
574
4 067
-638
29 507
y
i
=
10
x
i
+
ε
i
,
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaamyEamaaBa
aaleaacaWGPbaabeaakiaai2dacaaIXaGaaGimaiaadIhadaWgaaWc
baGaamyAaaqabaGccqGHRaWkcqaH1oqzdaWgaaWcbaGaamyAaaqaba
GccaGGSaaaaa@41FC@
avec
ε
i
∼
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaeqyTdu2aaS
baaSqaaiaadMgaaeqaaOGaeSipIOdaaa@3B14@
i.i.d.
t
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaamiDaaaa@3819@
de Student avec
ν
=
5
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaeqyVd4MaaG
ypaiaaiwdaaaa@3A5E@
V
˜
(
F
˜
s
(
t
)
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOvayaaia
WaaeWabeaaceWGgbGbaGaadaWgaaWcbaGaam4CaaqabaGcdaqadaqa
aiaadshaaiaawIcacaGLPaaaaiaawIcacaGLPaaaaaa@3E1E@
-2 170
11 624
-1 027
2 480
-816
3 274
-1 424
2 583
-1 946
8 681
V
˜
(
F
˜
l
(
t
)
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOvayaaia
WaaeWabeaaceWGgbGbaGaadaWgaaWcbaGaamiBaaqabaGcdaqadaqa
aiaadshaaiaawIcacaGLPaaaaiaawIcacaGLPaaaaaa@3E17@
-1 534
11 605
-529
2 632
-148
2 975
-859
2 590
-1 151
9 015
V
˜
(
F
˜
s
*
(
t
)
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOvayaaia
WaaeWabeaaceWGgbGbaGaadaqhaaWcbaGaam4CaaqaaiaaiQcaaaGc
daqadaqaaiaadshaaiaawIcacaGLPaaaaiaawIcacaGLPaaaaaa@3ED3@
-1 765
12 107
-1 108
2 529
-714
3 366
-1 318
2 660
-1 905
8 658
V
˜
(
F
˜
l
*
(
t
)
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOvayaaia
WaaeWabeaaceWGgbGbaGaadaqhaaWcbaGaamiBaaqaaiaaiQcaaaGc
daqadaqaaiaadshaaiaawIcacaGLPaaaaiaawIcacaGLPaaaaaa@3ECC@
-1 062
11 948
-671
2 735
-212
3 291
-762
2 785
-1 048
8 590
V
˜
(
F
˜
π
(
t
)
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOvayaaia
WaaeWabeaaceWGgbGbaGaadaWgaaWcbaGaeqiWdahabeaakmaabmaa
baGaamiDaaGaayjkaiaawMcaaaGaayjkaiaawMcaaaaa@3EE3@
254
31 545
-52
3 726
136
4 152
267
3 992
35
30 264
y
i
=
10
x
i
+
ε
i
,
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaamyEamaaBa
aaleaacaWGPbaabeaakiaai2dacaaIXaGaaGimaiaadIhadaWgaaWc
baGaamyAaaqabaGccqGHRaWkcqaH1oqzdaWgaaWcbaGaamyAaaqaba
GccaGGSaaaaa@41FC@
avec
ε
i
∼
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaeqyTdu2aaS
baaSqaaiaadMgaaeqaaOGaeSipIOdaaa@3B14@
indép.
t
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaamiDaaaa@3819@
de Student non centrale avec
ν
=
5
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaeqyVd4MaaG
ypaiaaiwdaaaa@3A5E@
et
μ
=
15
x
i
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaeqiVd0MaaG
ypaiaaigdacaaI1aGaamiEamaaBaaaleaacaWGPbaabeaaaaa@3D2E@
V
˜
(
F
˜
s
(
t
)
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOvayaaia
WaaeWabeaaceWGgbGbaGaadaWgaaWcbaGaam4CaaqabaGcdaqadaqa
aiaadshaaiaawIcacaGLPaaaaiaawIcacaGLPaaaaaa@3E1E@
-1 642
25 809
-855
3 541
-1 076
3 038
-1 081
3 030
-1 361
21 157
V
˜
(
F
˜
l
(
t
)
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOvayaaia
WaaeWabeaaceWGgbGbaGaadaWgaaWcbaGaamiBaaqabaGcdaqadaqa
aiaadshaaiaawIcacaGLPaaaaiaawIcacaGLPaaaaaa@3E17@
-950
25 692
-323
3 509
-597
3 312
-617
3 164
-1 124
20 231
V
˜
(
F
˜
s
*
(
t
)
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOvayaaia
WaaeWabeaaceWGgbGbaGaadaqhaaWcbaGaam4CaaqaaiaaiQcaaaGc
daqadaqaaiaadshaaiaawIcacaGLPaaaaiaawIcacaGLPaaaaaa@3ED3@
-1 385
26 406
-997
3 505
-1 089
3 045
-1 096
3 033
-1 310
21 393
V
˜
(
F
˜
l
*
(
t
)
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOvayaaia
WaaeWabeaaceWGgbGbaGaadaqhaaWcbaGaamiBaaqaaiaaiQcaaaGc
daqadaqaaiaadshaaiaawIcacaGLPaaaaiaawIcacaGLPaaaaaa@3ECC@
-832
26 212
-292
3 556
-614
3 317
-716
3 154
-1 135
20 286
V
˜
(
F
˜
π
(
t
)
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOvayaaia
WaaeWabeaaceWGgbGbaGaadaWgaaWcbaGaeqiWdahabeaakmaabmaa
baGaamiDaaGaayjkaiaawMcaaaGaayjkaiaawMcaaaaa@3EE3@
105
29 621
507
3 857
209
4 244
425
3 910
-337
29 082
y
i
=
10
x
i
1
/
4
+
ε
i
,
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaamyEamaaBa
aaleaacaWGPbaabeaakiaai2dacaaIXaGaaGimaiaadIhadaqhaaWc
baGaamyAaaqaamaalyaabaGaaGymaaqaaiaaisdaaaaaaOGaey4kaS
IaeqyTdu2aaSbaaSqaaiaadMgaaeqaaOGaaiilaaaa@438C@
avec
ε
i
∼
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaeqyTdu2aaS
baaSqaaiaadMgaaeqaaOGaeSipIOdaaa@3B14@
i.i.d.
t
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaamiDaaaa@3819@
de Student avec
ν
=
5
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaeqyVd4MaaG
ypaiaaiwdaaaa@3A5E@
V
˜
(
F
˜
s
(
t
)
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOvayaaia
WaaeWabeaaceWGgbGbaGaadaWgaaWcbaGaam4CaaqabaGcdaqadaqa
aiaadshaaiaawIcacaGLPaaaaiaawIcacaGLPaaaaaa@3E1E@
-2 465
30 612
-1 121
4 594
-1 512
3 183
-1 958
3 076
-863
19 720
V
˜
(
F
˜
l
(
t
)
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOvayaaia
WaaeWabeaaceWGgbGbaGaadaWgaaWcbaGaamiBaaqabaGcdaqadaqa
aiaadshaaiaawIcacaGLPaaaaiaawIcacaGLPaaaaaa@3E17@
-1 780
28 103
-663
4 420
-1 092
3 319
-1 491
3 140
-439
18 985
V
˜
(
F
˜
s
*
(
t
)
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOvayaaia
WaaeWabeaaceWGgbGbaGaadaqhaaWcbaGaam4CaaqaaiaaiQcaaaGc
daqadaqaaiaadshaaiaawIcacaGLPaaaaiaawIcacaGLPaaaaaa@3ED3@
-2 052
33 980
-1 150
4 619
-1 537
3 217
-1 948
3 127
-954
19 637
V
˜
(
F
˜
l
*
(
t
)
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOvayaaia
WaaeWabeaaceWGgbGbaGaadaqhaaWcbaGaamiBaaqaaiaaiQcaaaGc
daqadaqaaiaadshaaiaawIcacaGLPaaaaiaawIcacaGLPaaaaaa@3ECC@
-1 194
33 573
-691
4 472
-1 124
3 368
-1 438
3 228
-357
19 245
V
˜
(
F
˜
π
(
t
)
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOvayaaia
WaaeWabeaaceWGgbGbaGaadaWgaaWcbaGaeqiWdahabeaakmaabmaa
baGaamiDaaGaayjkaiaawMcaaaGaayjkaiaawMcaaaaa@3EE3@
-81
30 001
9
3 756
-110
3 996
-598
3 661
440
32 455
y
i
=
10
x
i
1
/
4
+
ε
i
,
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaamyEamaaBa
aaleaacaWGPbaabeaakiaai2dacaaIXaGaaGimaiaadIhadaqhaaWc
baGaamyAaaqaamaalyaabaGaaGymaaqaaiaaisdaaaaaaOGaey4kaS
IaeqyTdu2aaSbaaSqaaiaadMgaaeqaaOGaaiilaaaa@438C@
avec
ε
i
∼
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaeqyTdu2aaS
baaSqaaiaadMgaaeqaaOGaeSipIOdaaa@3B14@
indép.
t
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaamiDaaaa@3819@
de Student non centrale avec
ν
=
5
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaeqyVd4MaaG
ypaiaaiwdaaaa@3A5E@
et
μ
=
15
x
i
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaeqiVd0MaaG
ypaiaaigdacaaI1aGaamiEamaaBaaaleaacaWGPbaabeaaaaa@3D2E@
V
˜
(
F
˜
s
(
t
)
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOvayaaia
WaaeWabeaaceWGgbGbaGaadaWgaaWcbaGaam4CaaqabaGcdaqadaqa
aiaadshaaiaawIcacaGLPaaaaiaawIcacaGLPaaaaaa@3E1E@
-1 873
29 437
-758
3 759
-621
3 476
-709
3 599
-1 298
27 679
V
˜
(
F
˜
l
(
t
)
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOvayaaia
WaaeWabeaaceWGgbGbaGaadaWgaaWcbaGaamiBaaqabaGcdaqadaqa
aiaadshaaiaawIcacaGLPaaaaiaawIcacaGLPaaaaaa@3E17@
-1 267
28 511
-284
3 661
-131
3 758
-321
3 552
-1 075
26 790
V
˜
(
F
˜
s
*
(
t
)
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOvayaaia
WaaeWabeaaceWGgbGbaGaadaqhaaWcbaGaam4CaaqaaiaaiQcaaaGc
daqadaqaaiaadshaaiaawIcacaGLPaaaaiaawIcacaGLPaaaaaa@3ED3@
-1 710
30 670
-928
3 741
-628
3 510
-777
3 603
-1 245
27 972
V
˜
(
F
˜
l
*
(
t
)
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOvayaaia
WaaeWabeaaceWGgbGbaGaadaqhaaWcbaGaamiBaaqaaiaaiQcaaaGc
daqadaqaaiaadshaaiaawIcacaGLPaaaaiaawIcacaGLPaaaaaa@3ECC@
-939
30 486
-270
3 764
-171
3 803
-375
3 581
-1 014
26 926
V
˜
(
F
˜
π
(
t
)
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOvayaaia
WaaeWabeaaceWGgbGbaGaadaWgaaWcbaGaeqiWdahabeaakmaabmaa
baGaamiDaaGaayjkaiaawMcaaaGaayjkaiaawMcaaaaa@3EE3@
178
29 640
599
3 816
533
4 324
590
3 874
-404
28 917
Tableau 5.6
Populations artificielles (taille de population
N = 1 000 ) .
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqipu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peub0dXxdrpe0=1qpeea0=yrVue9
Fve9Fve8meqabeqadiWaceGabeqabeWabeqaeeaakeaadaqacaqaai
aad6eacqGH9aqpcaaIXaGaaGjbVlaaicdacaaIWaGaaGimaaGaayzk
aaGaaiOlaaaa@3FF8@
BIAISR et REQMR des estimateurs de variance sous échantillonnage de Poisson avec probabilités d’inclusion dans l’échantillon
π
i
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqipu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peub0dXxdrpe0=1qpeea0=yrVue9
Fve9Fve8meqabeqadiWaceGabeqabeWabeqaeeaakeaacqaHapaCda
WgaaWcbaGaamyAaaqabaaaaa@3B06@
proportionnelles aux écarts-types des lois
t
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqipu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peub0dXxdrpe0=1qpeea0=yrVue9
Fve9Fve8meqabeqadiWaceGabeqabeWabeqaeeaakeaacaWG0baaaa@3928@
de Student non centrale avec
v = 5
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqipu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peub0dXxdrpe0=1qpeea0=yrVue9
Fve9Fve8meqabeqadiWaceGabeqabeWabeqaeeaakeaacaWG2bGaey
ypa0JaaGynaaaa@3AEF@
dl et avec paramètre de non-centralité
μ = 15
x
i
.
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqipu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peub0dXxdrpe0=1qpeea0=yrVue9
Fve9Fve8meqabeqadiWaceGabeqabeWabeqaeeaakeaacqaH8oqBcq
GH9aqpcaaIXaGaaGynaiaadIhadaWgaaWcbaGaamyAaaqabaGccaGG
Uaaaaa@3F38@
Taille espérée d’échantillon
n
*
= 100
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqipu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peub0dXxdrpe0=1qpeea0=yrVue9
Fve9Fve8meqabeqadiWaceGabeqabeWabeqaeeaakeaacaWGUbWaaW
baaSqabeaacaGGQaaaaOGaeyypa0JaaGymaiaaicdacaaIWaaaaa@3D3C@
Sommaire du tableau
Le tableau montre les résultats de Populations artificielles (taille de population XXXX BIAISR et REQM des estimateurs de variance sous échantillonnage de Poisson avec probabilités d’inclusion dans l’échantillon XXXX proportionnelles aux écarts-types des lois XXXX de Student non centrale avec XXXX dl et avec paramètre de non-centralité XXXX Taille espérée d’échantillon XXXX. Les données sont présentées selon (titres de rangée) et XXXX, BIAISR , REQM et REQM , calculées selon avec XXXX i.i.d. XXXX de Student centrale avec XXXX unités de mesure (figurant comme en-tête de colonne).
t
=
F
N
−
1
(
0,05
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbeqabeWacmGabiqabeqabmqabeabbaGcbaGaamiDaiaai2
dacaWGgbWaa0baaSqaaiaad6eaaeaacqGHsislcaaIXaaaaOWaaeWa
aeaacaaIWaGaaGOlaiaaicdacaaI1aaacaGLOaGaayzkaaaaaa@40DB@
t
=
F
N
−
1
(
0,25
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbeqabeWacmGabiqabeqabmqabeabbaGcbaGaamiDaiaai2
dacaWGgbWaa0baaSqaaiaad6eaaeaacqGHsislcaaIXaaaaOWaaeWa
aeaacaaIWaGaaGOlaiaaikdacaaI1aaacaGLOaGaayzkaaaaaa@40DD@
t
=
F
N
−
1
(
0,50
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbeqabeWacmGabiqabeqabmqabeabbaGcbaGaamiDaiaai2
dacaWGgbWaa0baaSqaaiaad6eaaeaacqGHsislcaaIXaaaaOWaaeWa
aeaacaaIWaGaaGOlaiaaiwdacaaIWaaacaGLOaGaayzkaaaaaa@40DB@
t
=
F
N
−
1
(
0,75
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbeqabeWacmGabiqabeqabmqabeabbaGcbaGaamiDaiaai2
dacaWGgbWaa0baaSqaaiaad6eaaeaacqGHsislcaaIXaaaaOWaaeWa
aeaacaaIWaGaaGOlaiaaiEdacaaI1aaacaGLOaGaayzkaaaaaa@40E2@
t
=
F
N
−
1
(
0,95
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbeqabeWacmGabiqabeqabmqabeabbaGcbaGaamiDaiaai2
dacaWGgbWaa0baaSqaaiaad6eaaeaacqGHsislcaaIXaaaaOWaaeWa
aeaacaaIWaGaaGOlaiaaiMdacaaI1aaacaGLOaGaayzkaaaaaa@40E4@
BIAISR
REQMR
BIAISR
REQMR
BIAISR
REQMR
BIAISR
REQMR
BIAISR
REQMR
y
i
=
ε
i
,
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaamyEamaaBa
aaleaacaWGPbaabeaakiaai2dacqaH1oqzdaWgaaWcbaGaamyAaaqa
baGccaGGSaaaaa@3D84@
avec
ε
i
∼
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaeqyTdu2aaS
baaSqaaiaadMgaaeqaaOGaeSipIOdaaa@3B14@
i.i.d.
t
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaamiDaaaa@3819@
de Student centrale avec
ν
=
5
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaeqyVd4MaaG
ypaiaaiwdaaaa@3A5E@
V
˜
(
F
˜
s
(
t
)
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOvayaaia
WaaeWabeaaceWGgbGbaGaadaWgaaWcbaGaam4CaaqabaGcdaqadaqa
aiaadshaaiaawIcacaGLPaaaaiaawIcacaGLPaaaaaa@3E1E@
-3 306
65 777
-4 248
8 032
-5 093
4 242
-6 258
4 844
-5 652
32 037
V
˜
(
F
˜
l
(
t
)
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOvayaaia
WaaeWabeaaceWGgbGbaGaadaWgaaWcbaGaamiBaaqabaGcdaqadaqa
aiaadshaaiaawIcacaGLPaaaaiaawIcacaGLPaaaaaa@3E17@
-2 048
47 035
-2 656
4 705
-2 434
3 116
-3 310
3 939
-3 092
29 380
V
˜
(
F
˜
s
*
(
t
)
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOvayaaia
WaaeWabeaaceWGgbGbaGaadaqhaaWcbaGaam4CaaqaaiaaiQcaaaGc
daqadaqaaiaadshaaiaawIcacaGLPaaaaiaawIcacaGLPaaaaaa@3ED3@
-3 362
36 855
-2 488
4 409
-1 910
3 147
-2 869
3 910
-4 329
23 247
V
˜
(
F
˜
l
*
(
t
)
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOvayaaia
WaaeWabeaaceWGgbGbaGaadaqhaaWcbaGaamiBaaqaaiaaiQcaaaGc
daqadaqaaiaadshaaiaawIcacaGLPaaaaiaawIcacaGLPaaaaaa@3ECC@
-2 696
39 509
-2 076
4 450
-1 768
3 163
-2 648
3 811
-3 244
26 343
V
˜
(
F
˜
π
(
t
)
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOvayaaia
WaaeWabeaaceWGgbGbaGaadaWgaaWcbaGaeqiWdahabeaakmaabmaa
baGaamiDaaGaayjkaiaawMcaaaGaayjkaiaawMcaaaaa@3EE3@
113
129 637
259
15 120
618
6 327
193
5 429
273
6 097
y
i
=
ε
i
,
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaamyEamaaBa
aaleaacaWGPbaabeaakiaai2dacqaH1oqzdaWgaaWcbaGaamyAaaqa
baGccaGGSaaaaa@3D84@
avec
ε
i
∼
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaeqyTdu2aaS
baaSqaaiaadMgaaeqaaOGaeSipIOdaaa@3B14@
indép.
t
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaamiDaaaa@3819@
de Student non centrale avec
ν
=
5
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaeqyVd4MaaG
ypaiaaiwdaaaa@3A5E@
et
μ
=
15
x
i
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaeqiVd0MaaG
ypaiaaigdacaaI1aGaamiEamaaBaaaleaacaWGPbaabeaaaaa@3D2E@
V
˜
(
F
˜
s
(
t
)
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOvayaaia
WaaeWabeaaceWGgbGbaGaadaWgaaWcbaGaam4CaaqabaGcdaqadaqa
aiaadshaaiaawIcacaGLPaaaaiaawIcacaGLPaaaaaa@3E1E@
-740
125 975
-2 522
14 864
-5 466
3 658
-4 896
6 691
-1 551
83 262
V
˜
(
F
˜
l
(
t
)
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOvayaaia
WaaeWabeaaceWGgbGbaGaadaWgaaWcbaGaamiBaaqabaGcdaqadaqa
aiaadshaaiaawIcacaGLPaaaaiaawIcacaGLPaaaaaa@3E17@
-391
83 047
-1 503
8 946
-2 428
4 099
-2 228
5 526
-1 154
54 680
V
˜
(
F
˜
s
*
(
t
)
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOvayaaia
WaaeWabeaaceWGgbGbaGaadaqhaaWcbaGaam4CaaqaaiaaiQcaaaGc
daqadaqaaiaadshaaiaawIcacaGLPaaaaiaawIcacaGLPaaaaaa@3ED3@
-3 260
58 072
-2 649
7 661
-2 260
3 936
-2 795
5 011
-2 116
48 739
V
˜
(
F
˜
l
*
(
t
)
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOvayaaia
WaaeWabeaaceWGgbGbaGaadaqhaaWcbaGaamiBaaqaaiaaiQcaaaGc
daqadaqaaiaadshaaiaawIcacaGLPaaaaiaawIcacaGLPaaaaaa@3ECC@
-716
77 935
-2 000
7 979
-1 934
4 235
-2 279
5 243
-1 243
52 531
V
˜
(
F
˜
π
(
t
)
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOvayaaia
WaaeWabeaaceWGgbGbaGaadaWgaaWcbaGaeqiWdahabeaakmaabmaa
baGaamiDaaGaayjkaiaawMcaaaGaayjkaiaawMcaaaaa@3EE3@
666
251 134
-564
26 553
-87
7 344
-2
6 029
407
6 610
y
i
=
10
x
i
+
ε
i
,
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaamyEamaaBa
aaleaacaWGPbaabeaakiaai2dacaaIXaGaaGimaiaadIhadaWgaaWc
baGaamyAaaqabaGccqGHRaWkcqaH1oqzdaWgaaWcbaGaamyAaaqaba
GccaGGSaaaaa@41FC@
avec
ε
i
∼
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaeqyTdu2aaS
baaSqaaiaadMgaaeqaaOGaeSipIOdaaa@3B14@
i.i.d.
t
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaamiDaaaa@3819@
de Student avec
ν
=
5
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaeqyVd4MaaG
ypaiaaiwdaaaa@3A5E@
V
˜
(
F
˜
s
(
t
)
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOvayaaia
WaaeWabeaaceWGgbGbaGaadaWgaaWcbaGaam4CaaqabaGcdaqadaqa
aiaadshaaiaawIcacaGLPaaaaiaawIcacaGLPaaaaaa@3E1E@
-6 801
7 898
-6 470
4 281
-1 059
22 596
-398
32 401
-1 650
72 632
V
˜
(
F
˜
l
(
t
)
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOvayaaia
WaaeWabeaaceWGgbGbaGaadaWgaaWcbaGaamiBaaqabaGcdaqadaqa
aiaadshaaiaawIcacaGLPaaaaiaawIcacaGLPaaaaaa@3E17@
-4 978
5 826
-2 898
4 473
-603
9 530
206
15 226
-1 157
40 466
V
˜
(
F
˜
s
*
(
t
)
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOvayaaia
WaaeWabeaaceWGgbGbaGaadaqhaaWcbaGaam4CaaqaaiaaiQcaaaGc
daqadaqaaiaadshaaiaawIcacaGLPaaaaiaawIcacaGLPaaaaaa@3ED3@
-4 520
6 691
-2 710
4 213
-3 245
6 723
-1 156
12 681
-2 458
32 907
V
˜
(
F
˜
l
*
(
t
)
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOvayaaia
WaaeWabeaaceWGgbGbaGaadaqhaaWcbaGaamiBaaqaaiaaiQcaaaGc
daqadaqaaiaadshaaiaawIcacaGLPaaaaiaawIcacaGLPaaaaaa@3ECC@
-4 226
6 206
-1 674
5 062
-978
7 874
55
12 781
-1 283
33 737
V
˜
(
F
˜
π
(
t
)
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOvayaaia
WaaeWabeaaceWGgbGbaGaadaWgaaWcbaGaeqiWdahabeaakmaabmaa
baGaamiDaaGaayjkaiaawMcaaaGaayjkaiaawMcaaaaa@3EE3@
-707
47 550
118
7 214
609
4 409
743
4 628
435
4 800
y
i
=
10
x
i
+
ε
i
,
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaamyEamaaBa
aaleaacaWGPbaabeaakiaai2dacaaIXaGaaGimaiaadIhadaWgaaWc
baGaamyAaaqabaGccqGHRaWkcqaH1oqzdaWgaaWcbaGaamyAaaqaba
GccaGGSaaaaa@41FC@
avec
ε
i
∼
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaeqyTdu2aaS
baaSqaaiaadMgaaeqaaOGaeSipIOdaaa@3B14@
indép.
t
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaamiDaaaa@3819@
de Student non centrale avec
ν
=
5
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaeqyVd4MaaG
ypaiaaiwdaaaa@3A5E@
et
μ
=
15
x
i
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaeqiVd0MaaG
ypaiaaigdacaaI1aGaamiEamaaBaaaleaacaWGPbaabeaaaaa@3D2E@
V
˜
(
F
˜
s
(
t
)
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOvayaaia
WaaeWabeaaceWGgbGbaGaadaWgaaWcbaGaam4CaaqabaGcdaqadaqa
aiaadshaaiaawIcacaGLPaaaaiaawIcacaGLPaaaaaa@3E1E@
-7 398
8 847
-6 235
3 667
-2 493
8 171
-1 051
16 299
-1 440
71 943
V
˜
(
F
˜
l
(
t
)
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOvayaaia
WaaeWabeaaceWGgbGbaGaadaWgaaWcbaGaamiBaaqabaGcdaqadaqa
aiaadshaaiaawIcacaGLPaaaaiaawIcacaGLPaaaaaa@3E17@
-4 548
9 463
-3 136
3 282
-1 187
4 246
-832
7 638
-982
45 182
V
˜
(
F
˜
s
*
(
t
)
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOvayaaia
WaaeWabeaaceWGgbGbaGaadaqhaaWcbaGaam4CaaqaaiaaiQcaaaGc
daqadaqaaiaadshaaiaawIcacaGLPaaaaiaawIcacaGLPaaaaaa@3ED3@
-3 902
11 727
-2 808
3 409
-2 411
3 501
-1 721
6 737
-1 671
41 389
V
˜
(
F
˜
l
*
(
t
)
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOvayaaia
WaaeWabeaaceWGgbGbaGaadaqhaaWcbaGaamiBaaqaaiaaiQcaaaGc
daqadaqaaiaadshaaiaawIcacaGLPaaaaiaawIcacaGLPaaaaaa@3ECC@
-3 598
10 771
-2 610
3 462
-1 284
3 988
-852
7 008
-972
43 017
V
˜
(
F
˜
π
(
t
)
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOvayaaia
WaaeWabeaaceWGgbGbaGaadaWgaaWcbaGaeqiWdahabeaakmaabmaa
baGaamiDaaGaayjkaiaawMcaaaGaayjkaiaawMcaaaaa@3EE3@
146
57 044
-42
8 708
520
4 784
214
4 686
390
5 085
y
i
=
10
x
i
1
/
4
+
ε
i
,
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaamyEamaaBa
aaleaacaWGPbaabeaakiaai2dacaaIXaGaaGimaiaadIhadaqhaaWc
baGaamyAaaqaamaalyaabaGaaGymaaqaaiaaisdaaaaaaOGaey4kaS
IaeqyTdu2aaSbaaSqaaiaadMgaaeqaaOGaaiilaaaa@438C@
avec
ε
i
∼
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaeqyTdu2aaS
baaSqaaiaadMgaaeqaaOGaeSipIOdaaa@3B14@
i.i.d.
t
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaamiDaaaa@3819@
de Student avec
ν
=
5
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaeqyVd4MaaG
ypaiaaiwdaaaa@3A5E@
V
˜
(
F
˜
s
(
t
)
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOvayaaia
WaaeWabeaaceWGgbGbaGaadaWgaaWcbaGaam4CaaqabaGcdaqadaqa
aiaadshaaiaawIcacaGLPaaaaiaawIcacaGLPaaaaaa@3E1E@
-7 731
8 568
-6 597
3 484
-2 442
7 775
-903
16 067
-1 967
56 480
V
˜
(
F
˜
l
(
t
)
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOvayaaia
WaaeWabeaaceWGgbGbaGaadaWgaaWcbaGaamiBaaqabaGcdaqadaqa
aiaadshaaiaawIcacaGLPaaaaiaawIcacaGLPaaaaaa@3E17@
-4 611
9 378
-2 990
3 252
-874
4 119
-347
7 420
-1 310
35 051
V
˜
(
F
˜
s
*
(
t
)
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOvayaaia
WaaeWabeaaceWGgbGbaGaadaqhaaWcbaGaam4CaaqaaiaaiQcaaaGc
daqadaqaaiaadshaaiaawIcacaGLPaaaaiaawIcacaGLPaaaaaa@3ED3@
-4 747
11 909
-2 679
3 298
-1 896
3 272
-2 248
5 747
-3 382
27 222
V
˜
(
F
˜
l
*
(
t
)
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOvayaaia
WaaeWabeaaceWGgbGbaGaadaqhaaWcbaGaamiBaaqaaiaaiQcaaaGc
daqadaqaaiaadshaaiaawIcacaGLPaaaaiaawIcacaGLPaaaaaa@3ECC@
-4 223
10 380
-2 100
3 494
-788
3 731
-550
5 975
-1 795
29 856
V
˜
(
F
˜
π
(
t
)
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOvayaaia
WaaeWabeaaceWGgbGbaGaadaWgaaWcbaGaeqiWdahabeaakmaabmaa
baGaamiDaaGaayjkaiaawMcaaaGaayjkaiaawMcaaaaa@3EE3@
-428
47 038
-206
7 350
641
4 504
738
4 708
487
4 943
y
i
=
10
x
i
1
/
4
+
ε
i
,
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaamyEamaaBa
aaleaacaWGPbaabeaakiaai2dacaaIXaGaaGimaiaadIhadaqhaaWc
baGaamyAaaqaamaalyaabaGaaGymaaqaaiaaisdaaaaaaOGaey4kaS
IaeqyTdu2aaSbaaSqaaiaadMgaaeqaaOGaaiilaaaa@438C@
avec
ε
i
∼
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaeqyTdu2aaS
baaSqaaiaadMgaaeqaaOGaeSipIOdaaa@3B14@
indép.
t
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaamiDaaaa@3819@
de Student non centrale avec
ν
=
5
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaeqyVd4MaaG
ypaiaaiwdaaaa@3A5E@
et
μ
=
15
x
i
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaeqiVd0MaaG
ypaiaaigdacaaI1aGaamiEamaaBaaaleaacaWGPbaabeaaaaa@3D2E@
V
˜
(
F
˜
s
(
t
)
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOvayaaia
WaaeWabeaaceWGgbGbaGaadaWgaaWcbaGaam4CaaqabaGcdaqadaqa
aiaadshaaiaawIcacaGLPaaaaiaawIcacaGLPaaaaaa@3E1E@
-4 936
40 696
-6 111
4 579
-5 549
4 035
-1 864
14 381
-1 509
84 892
V
˜
(
F
˜
l
(
t
)
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOvayaaia
WaaeWabeaaceWGgbGbaGaadaWgaaWcbaGaamiBaaqabaGcdaqadaqa
aiaadshaaiaawIcacaGLPaaaaiaawIcacaGLPaaaaaa@3E17@
-3 004
29 404
-2 764
3 962
-2 436
3 606
-1 234
7 357
-1 103
53 875
V
˜
(
F
˜
s
*
(
t
)
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOvayaaia
WaaeWabeaaceWGgbGbaGaadaqhaaWcbaGaam4CaaqaaiaaiQcaaaGc
daqadaqaaiaadshaaiaawIcacaGLPaaaaiaawIcacaGLPaaaaaa@3ED3@
-4 328
27 704
-2 516
4 235
-2 671
3 332
-2 586
5 955
-1 939
47 601
V
˜
(
F
˜
l
*
(
t
)
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOvayaaia
WaaeWabeaaceWGgbGbaGaadaqhaaWcbaGaamiBaaqaaiaaiQcaaaGc
daqadaqaaiaadshaaiaawIcacaGLPaaaaiaawIcacaGLPaaaaaa@3ECC@
-3 454
28 267
-2 263
4 160
-2 329
3 574
-1 433
6 682
-1 171
50 985
V
˜
(
F
˜
π
(
t
)
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOvayaaia
WaaeWabeaaceWGgbGbaGaadaWgaaWcbaGaeqiWdahabeaakmaabmaa
baGaamiDaaGaayjkaiaawMcaaaGaayjkaiaawMcaaaaa@3EE3@
152
98 607
663
12 879
15
5 376
20
5 080
429
5 619
Tableau 5.7
Populations réelles (taille de population
N = 284 ) .
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqipu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peub0dXxdrpe0=1qpeea0=yrVue9
Fve9Fve8meqabeqadiWaceGabeqabeWabeqaeeaakeaadaqacaqaai
aad6eacqGH9aqpcaaIYaGaaGioaiaaisdaaiaawMcaaiaac6caaaa@3DBE@
BIAISR et REQMR des estimateurs de variance sous échantillonnage aléatoire simple sans remise. Taille d’échantillon
n = 30
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqipu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peub0dXxdrpe0=1qpeea0=yrVue9
Fve9Fve8meqabeqadiWaceGabeqabeWabeqaeeaakeaacaWGUbGaey
ypa0JaaG4maiaaicdaaaa@3B9F@
Sommaire du tableau
Le tableau montre les résultats de Populations réelles (taille de population XXXX BIAISR et REQM des estimateurs de variance sous échantillonnage aléatoire simple sans remise. Taille d’échantillon XXXX XXXX, BIAISR , REQM et REQM , calculées selon Population MU284 avec XXXX et XXXX et Population MU284 avec XXXX et XXXX unités de mesure (figurant comme en-tête de colonne).
t
=
F
N
−
1
(
0,05
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbeqabeWacmGabiqabeqabmqabeabbaGcbaGaamiDaiaai2
dacaWGgbWaa0baaSqaaiaad6eaaeaacqGHsislcaaIXaaaaOWaaeWa
aeaacaaIWaGaaGOlaiaaicdacaaI1aaacaGLOaGaayzkaaaaaa@40DB@
t
=
F
N
−
1
(
0,25
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbeqabeWacmGabiqabeqabmqabeabbaGcbaGaamiDaiaai2
dacaWGgbWaa0baaSqaaiaad6eaaeaacqGHsislcaaIXaaaaOWaaeWa
aeaacaaIWaGaaGOlaiaaikdacaaI1aaacaGLOaGaayzkaaaaaa@40DD@
t
=
F
N
−
1
(
0,50
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbeqabeWacmGabiqabeqabmqabeabbaGcbaGaamiDaiaai2
dacaWGgbWaa0baaSqaaiaad6eaaeaacqGHsislcaaIXaaaaOWaaeWa
aeaacaaIWaGaaGOlaiaaiwdacaaIWaaacaGLOaGaayzkaaaaaa@40DB@
t
=
F
N
−
1
(
0,75
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbeqabeWacmGabiqabeqabmqabeabbaGcbaGaamiDaiaai2
dacaWGgbWaa0baaSqaaiaad6eaaeaacqGHsislcaaIXaaaaOWaaeWa
aeaacaaIWaGaaGOlaiaaiEdacaaI1aaacaGLOaGaayzkaaaaaa@40E2@
t
=
F
N
−
1
(
0,95
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbeqabeWacmGabiqabeqabmqabeabbaGcbaGaamiDaiaai2
dacaWGgbWaa0baaSqaaiaad6eaaeaacqGHsislcaaIXaaaaOWaaeWa
aeaacaaIWaGaaGOlaiaaiMdacaaI1aaacaGLOaGaayzkaaaaaa@40E4@
BIAISR
REQMR
BIAISR
REQMR
BIAISR
REQMR
BIAISR
REQMR
BIAISR
REQMR
Population MU284 avec
Y
=
ln
R
M
T
85
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaamywaiaai2
daciGGSbGaaiOBaiaadkfacaWGnbGaamivaiaaiIdacaaI1aaaaa@3EAC@
et
X
=
ln
P
85
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaamiwaiaai2
daciGGSbGaaiOBaiaadcfacaaI4aGaaGynaaaa@3CFE@
V
˜
(
F
˜
s
(
t
)
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOvayaaia
WaaeWabeaaceWGgbGbaGaadaWgaaWcbaGaam4CaaqabaGcdaqadaqa
aiaadshaaiaawIcacaGLPaaaaiaawIcacaGLPaaaaaa@3E1E@
-2 853
16 809
-1 700
3 037
-1 554
2 984
-1 100
4 633
-5 503
16 257
V
˜
(
F
˜
l
(
t
)
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOvayaaia
WaaeWabeaaceWGgbGbaGaadaWgaaWcbaGaamiBaaqabaGcdaqadaqa
aiaadshaaiaawIcacaGLPaaaaiaawIcacaGLPaaaaaa@3E17@
-1 110
16 374
-1 827
2 760
-1 683
2 847
-927
4 387
-3 016
18 685
V
˜
(
F
˜
s
*
(
t
)
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOvayaaia
WaaeWabeaaceWGgbGbaGaadaqhaaWcbaGaam4CaaqaaiaaiQcaaaGc
daqadaqaaiaadshaaiaawIcacaGLPaaaaiaawIcacaGLPaaaaaa@3ED3@
-1 043
19 081
-91
7 728
-448
9 120
-484
7 715
-1 877
65 298
V
˜
(
F
˜
l
*
(
t
)
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOvayaaia
WaaeWabeaaceWGgbGbaGaadaqhaaWcbaGaamiBaaqaaiaaiQcaaaGc
daqadaqaaiaadshaaiaawIcacaGLPaaaaiaawIcacaGLPaaaaaa@3ECC@
-424
18 971
104
7 819
-382
9 110
-301
7 799
-1 058
62 968
V
˜
(
F
˜
π
(
t
)
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOvayaaia
WaaeWabeaaceWGgbGbaGaadaWgaaWcbaGaeqiWdahabeaakmaabmaa
baGaamiDaaGaayjkaiaawMcaaaGaayjkaiaawMcaaaaa@3EE3@
-186
29 720
-603
3 901
31
3 971
500
4 383
-74
28 418
Population MU284 avec
Y
=
ln
R
M
T
85
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaamywaiaai2
daciGGSbGaaiOBaiaadkfacaWGnbGaamivaiaaiIdacaaI1aaaaa@3EAC@
et
X
=
ln
R
E
V
84
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaamiwaiaai2
daciGGSbGaaiOBaiaadkfacaWGfbGaamOvaiaaiIdacaaI0aaaaa@3EA4@
V
˜
(
F
˜
s
(
t
)
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOvayaaia
WaaeWabeaaceWGgbGbaGaadaWgaaWcbaGaam4CaaqabaGcdaqadaqa
aiaadshaaiaawIcacaGLPaaaaiaawIcacaGLPaaaaaa@3E1E@
-2 283
16 303
-1 450
3 538
-945
3 526
-1 071
4 300
-4 832
19 401
V
˜
(
F
˜
l
(
t
)
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOvayaaia
WaaeWabeaaceWGgbGbaGaadaWgaaWcbaGaamiBaaqabaGcdaqadaqa
aiaadshaaiaawIcacaGLPaaaaiaawIcacaGLPaaaaaa@3E17@
-1 095
16 755
-1 427
3 181
-938
3 390
-780
4 051
-2 753
20 551
V
˜
(
F
˜
s
*
(
t
)
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOvayaaia
WaaeWabeaaceWGgbGbaGaadaqhaaWcbaGaam4CaaqaaiaaiQcaaaGc
daqadaqaaiaadshaaiaawIcacaGLPaaaaiaawIcacaGLPaaaaaa@3ED3@
-1 737
14 642
-298
5 648
-546
5 282
-736
5 679
-3 564
38 344
V
˜
(
F
˜
l
*
(
t
)
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOvayaaia
WaaeWabeaaceWGgbGbaGaadaqhaaWcbaGaamiBaaqaaiaaiQcaaaGc
daqadaqaaiaadshaaiaawIcacaGLPaaaaiaawIcacaGLPaaaaaa@3ECC@
-1 174
14 111
-27
5 856
-422
5 452
-228
5 974
-1 433
43 923
V
˜
(
F
˜
π
(
t
)
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOvayaaia
WaaeWabeaaceWGgbGbaGaadaWgaaWcbaGaeqiWdahabeaakmaabmaa
baGaamiDaaGaayjkaiaawMcaaaGaayjkaiaawMcaaaaa@3EE3@
-307
28 421
-460
3 963
-344
3 850
112
4 235
-401
27 987
Tableau 5.8
Populations réelles (taille de population
N = 284 ) .
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqipu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peub0dXxdrpe0=1qpeea0=yrVue9
Fve9Fve8meqabeqadiWaceGabeqabeWabeqaeeaakeaadaqacaqaai
aad6eacqGH9aqpcaaIYaGaaGioaiaaisdaaiaawMcaaiaac6caaaa@3DBE@
BIAISR et REQMR des estimateurs de variance sous échantillonnage de Poisson avec probabilités d’inclusion proportionnelles à la valeur absolue des résidus de la régression linéaire des valeurs
y
i
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqipu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peub0dXxdrpe0=1qpeea0=yrVue9
Fve9Fve8meqabeqadiWaceGabeqabeWabeqaeeaakeaacaWG5bWaaS
baaSqaaiaadMgaaeqaaaaa@3A47@
de la population sur les valeurs
x
i
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqipu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peub0dXxdrpe0=1qpeea0=yrVue9
Fve9Fve8meqabeqadiWaceGabeqabeWabeqaeeaakeaacaWG4bWaaS
baaSqaaiaadMgaaeqaaaaa@3A46@
de la population. Taille espérée
n
*
= 30
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqipu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peub0dXxdrpe0=1qpeea0=yrVue9
Fve9Fve8meqabeqadiWaceGabeqabeWabeqaeeaakeaacaWGUbWaaW
baaSqabeaacaGGQaaaaOGaeyypa0JaaG4maiaaicdaaaa@3C84@
Table summary
This table displays the results of Real populations (population size XXXX RBIAS and RRMSE of variance estimators under Poisson sampling with inclusion probabilities proportional to the absolute value of the residuals of the linear regression of the population XXXX values on the population XXXX values. Expected size XXXX XXXX, RBIAS , RRMSE and RRMSE, calculated using MU284 population with XXXX and XXXX and MU284 population with XXXX and XXXX units of measure (appearing as column headers).
t
=
F
N
−
1
(
0,05
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbeqabeWacmGabiqabeqabmqabeabbaGcbaGaamiDaiaai2
dacaWGgbWaa0baaSqaaiaad6eaaeaacqGHsislcaaIXaaaaOWaaeWa
aeaacaaIWaGaaGOlaiaaicdacaaI1aaacaGLOaGaayzkaaaaaa@40DB@
t
=
F
N
−
1
(
0,25
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbeqabeWacmGabiqabeqabmqabeabbaGcbaGaamiDaiaai2
dacaWGgbWaa0baaSqaaiaad6eaaeaacqGHsislcaaIXaaaaOWaaeWa
aeaacaaIWaGaaGOlaiaaikdacaaI1aaacaGLOaGaayzkaaaaaa@40DD@
t
=
F
N
−
1
(
0,50
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbeqabeWacmGabiqabeqabmqabeabbaGcbaGaamiDaiaai2
dacaWGgbWaa0baaSqaaiaad6eaaeaacqGHsislcaaIXaaaaOWaaeWa
aeaacaaIWaGaaGOlaiaaiwdacaaIWaaacaGLOaGaayzkaaaaaa@40DB@
t
=
F
N
−
1
(
0,75
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbeqabeWacmGabiqabeqabmqabeabbaGcbaGaamiDaiaai2
dacaWGgbWaa0baaSqaaiaad6eaaeaacqGHsislcaaIXaaaaOWaaeWa
aeaacaaIWaGaaGOlaiaaiEdacaaI1aaacaGLOaGaayzkaaaaaa@40E2@
t
=
F
N
−
1
(
0,95
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbeqabeWacmGabiqabeqabmqabeabbaGcbaGaamiDaiaai2
dacaWGgbWaa0baaSqaaiaad6eaaeaacqGHsislcaaIXaaaaOWaaeWa
aeaacaaIWaGaaGOlaiaaiMdacaaI1aaacaGLOaGaayzkaaaaaa@40E4@
BIAISR
REQMR
BIAISR
REQMR
BIAISR
REQMR
BIAISR
REQMR
BIAISR
REQMR
Population MU284 avec
Y
=
ln
R
M
T
85
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaamywaiaai2
daciGGSbGaaiOBaiaadkfacaWGnbGaamivaiaaiIdacaaI1aaaaa@3EAC@
et
X
=
ln
P
85
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaamiwaiaai2
daciGGSbGaaiOBaiaadcfacaaI4aGaaGynaaaa@3CFE@
V
˜
(
F
˜
s
(
t
)
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOvayaaia
WaaeWabeaaceWGgbGbaGaadaWgaaWcbaGaam4CaaqabaGcdaqadaqa
aiaadshaaiaawIcacaGLPaaaaiaawIcacaGLPaaaaaa@3E1E@
-3 502
26 342
-1 841
14 037
-2 691
12 087
-3 415
9 674
-5 932
26 823
V
˜
(
F
˜
l
(
t
)
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOvayaaia
WaaeWabeaaceWGgbGbaGaadaWgaaWcbaGaamiBaaqabaGcdaqadaqa
aiaadshaaiaawIcacaGLPaaaaiaawIcacaGLPaaaaaa@3E17@
-2 159
27 610
-1 782
14 010
-2 840
12 002
-3 186
10 177
-4 455
26 802
V
˜
(
F
˜
s
*
(
t
)
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOvayaaia
WaaeWabeaaceWGgbGbaGaadaqhaaWcbaGaam4CaaqaaiaaiQcaaaGc
daqadaqaaiaadshaaiaawIcacaGLPaaaaiaawIcacaGLPaaaaaa@3ED3@
-434
22 455
515
15 503
-506
31 296
-1 460
23 496
-2 649
78 527
V
˜
(
F
˜
l
*
(
t
)
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOvayaaia
WaaeWabeaaceWGgbGbaGaadaqhaaWcbaGaamiBaaqaaiaaiQcaaaGc
daqadaqaaiaadshaaiaawIcacaGLPaaaaiaawIcacaGLPaaaaaa@3ECC@
-80
22 921
677
15 575
-280
33 294
-1 283
26 612
-1 597
72 166
V
˜
(
F
˜
π
(
t
)
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOvayaaia
WaaeWabeaaceWGgbGbaGaadaWgaaWcbaGaeqiWdahabeaakmaabmaa
baGaamiDaaGaayjkaiaawMcaaaGaayjkaiaawMcaaaaa@3EE3@
-294
361 991
522
75 891
43
48 764
-241
36 354
90
32 354
Population MU284 avec
Y
=
ln
R
M
T
85
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaamywaiaai2
daciGGSbGaaiOBaiaadkfacaWGnbGaamivaiaaiIdacaaI1aaaaa@3EAC@
et
X
=
ln
R
E
V
84
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaamiwaiaai2
daciGGSbGaaiOBaiaadkfacaWGfbGaamOvaiaaiIdacaaI0aaaaa@3EA4@
V
˜
(
F
˜
s
(
t
)
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOvayaaia
WaaeWabeaaceWGgbGbaGaadaWgaaWcbaGaam4CaaqabaGcdaqadaqa
aiaadshaaiaawIcacaGLPaaaaiaawIcacaGLPaaaaaa@3E1E@
-5 220
18 699
-3 667
8 749
-3 222
7 537
-3 018
9 279
-4 955
44 597
V
˜
(
F
˜
l
(
t
)
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOvayaaia
WaaeWabeaaceWGgbGbaGaadaWgaaWcbaGaamiBaaqabaGcdaqadaqa
aiaadshaaiaawIcacaGLPaaaaiaawIcacaGLPaaaaaa@3E17@
-4 254
20 765
-3 100
9 180
-3 435
7 231
-3 196
8 540
-3 461
43 206
V
˜
(
F
˜
s
*
(
t
)
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOvayaaia
WaaeWabeaaceWGgbGbaGaadaqhaaWcbaGaam4CaaqaaiaaiQcaaaGc
daqadaqaaiaadshaaiaawIcacaGLPaaaaiaawIcacaGLPaaaaaa@3ED3@
-2 938
18 922
-1 110
11 828
-1 265
8 726
-1 040
10 963
-3 682
89 262
V
˜
(
F
˜
l
*
(
t
)
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOvayaaia
WaaeWabeaaceWGgbGbaGaadaqhaaWcbaGaamiBaaqaaiaaiQcaaaGc
daqadaqaaiaadshaaiaawIcacaGLPaaaaiaawIcacaGLPaaaaaa@3ECC@
-1 938
19 997
-699
12 641
-1 003
9 305
-599
11 545
-1 558
98 798
V
˜
(
F
˜
π
(
t
)
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGak0Jf9crFfpeea0xh9v8qiW7rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGabmOvayaaia
WaaeWabeaaceWGgbGbaGaadaWgaaWcbaGaeqiWdahabeaakmaabmaa
baGaamiDaaGaayjkaiaawMcaaaGaayjkaiaawMcaaaaa@3EE3@
-143
128 401
493
33 934
-255
18 473
-91
17 904
327
16 463
Comme le montrent les résultats des
simulations, les estimateurs de variance souffrent d’une grande variabilité. Ce
problème touche aussi l’estimateur de variance pour l’estimateur de Horvitz-Thompson qui, à l’occasion, présente de
très grandes REQMR . Il est en outre intéressant de noter que, si le BIAISR des
estimateurs de variance pour les estimateurs par la différence généralisée est
presque toujours négatif et parfois assez grand en valeur absolue, celui de
l’estimateur de variance pour l’estimateur de Horvitz-Thompson
est positif dans la plupart des cas considérés.
Remerciements
La présente étude a été financée en
partie par la subvention FAR 2014-ATE-0200 octroyée par University of Milano-Bicocca .
Annexe
Soit
β
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacqaHYoGyaa
a@3992@
une suite de nombres réels.
Tout au long de la présente annexe, nous désignerons par
O
i
1
,
i
2
,
…
,
i
k
(
β
)
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWGpbWaaS
baaSqaaiaadMgadaWgaaadbaGaaGymaaqabaWccaaISaGaamyAamaa
BaaameaacaaIYaaabeaaliaaiYcacqWIMaYscaaISaGaamyAamaaBa
aameaacaWGRbaabeaaaSqabaGcdaqadaqaaiabek7aIbGaayjkaiaa
wMcaaaaa@4542@
les termes de reste qui
peuvent dépendre de
x
i
1
,
x
i
2
,
…
,
x
i
k
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWG4bWaaS
baaSqaaiaadMgadaWgaaadbaGaaGymaaqabaaaleqaaOGaaGilaiaa
dIhadaWgaaWcbaGaamyAamaaBaaameaacaaIYaaabeaaaSqabaGcca
aISaGaeSOjGSKaaGilaiaadIhadaWgaaWcbaGaamyAamaaBaaameaa
caWGRbaabeaaaSqabaaaaa@449D@
et qui sont de même ordre que
la suite
β
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacqaHYoGyaa
a@3992@
uniformément pour
i
1
,
i
2
,
…
,
i
k
∈
U
.
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWGPbWaaS
baaSqaaiaaigdaaeqaaOGaaGilaiaadMgadaWgaaWcbaGaaGOmaaqa
baGccaaISaGaeSOjGSKaaGilaiaadMgadaWgaaWcbaGaam4Aaaqaba
GccqGHiiIZcaWGvbGaaiOlaaaa@4418@
Formellement,
R
(
x
i
1
,
x
i
2
,
…
,
x
i
k
)
=
O
i
1
,
i
2
,
…
,
i
k
(
β
)
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWGsbWaae
WaaeaacaWG4bWaaSbaaSqaaiaadMgadaWgaaadbaGaaGymaaqabaaa
leqaaOGaaGilaiaadIhadaWgaaWcbaGaamyAamaaBaaameaacaaIYa
aabeaaaSqabaGccaaISaGaeSOjGSKaaGilaiaadIhadaWgaaWcbaGa
amyAamaaBaaameaacaWGRbaabeaaaSqabaaakiaawIcacaGLPaaaca
aI9aGaam4tamaaBaaaleaacaWGPbWaaSbaaWqaaiaaigdaaeqaaSGa
aGilaiaadMgadaWgaaadbaGaaGOmaaqabaWccaaISaGaeSOjGSKaaG
ilaiaadMgadaWgaaadbaGaam4AaaqabaaaleqaaOWaaeWaaeaacqaH
YoGyaiaawIcacaGLPaaaaaa@551F@
si
sup
i
1
,
i
2
,
…
,
i
k
∈
U
|
R
(
x
i
1
,
x
i
2
,
…
,
x
i
k
)
|
=
O
(
β
)
.
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaadaGfqbqabS
qaaiaadMgadaWgaaadbaGaaGymaaqabaWccaaISaGaamyAamaaBaaa
meaacaaIYaaabeaaliaaiYcacqWIMaYscaaISaGaamyAamaaBaaame
aacaWGRbaabeaaliabgIGiolaaykW7caWGvbaabeGcbaGaci4Caiaa
cwhacaGGWbaaamaaemaabaGaaGPaVlaadkfadaqadaqaaiaadIhada
WgaaWcbaGaamyAamaaBaaabaGaaGymaaqabaaabeaakiaaiYcacaWG
4bWaaSbaaSqaaiaadMgadaWgaaqaaiaaikdaaeqaaaqabaGccaaISa
GaeSOjGSKaaGilaiaadIhadaWgaaWcbaGaamyAamaaBaaabaGaam4A
aaqabaaabeaaaOGaayjkaiaawMcaaiaaykW7aiaawEa7caGLiWoaca
aI9aGaam4tamaabmaabaGaeqOSdigacaGLOaGaayzkaaGaaGOlaaaa
@62E6@
En outre, pour simplifier la notation,
nous écrirons
m
i
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWGTbWaaS
baaSqaaiaadMgaaeqaaaaa@39FD@
à la place de
m
(
x
i
)
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWGTbWaae
WaaeaacaWG4bWaaSbaaSqaaiaadMgaaeqaaaGccaGLOaGaayzkaaaa
aa@3C8D@
et
σ
i
2
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacqaHdpWCda
qhaaWcbaGaamyAaaqaaiaaikdaaaaaaa@3B8B@
à la place de
σ
2
(
x
i
)
.
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacqaHdpWCda
ahaaWcbeqaaiaaikdaaaGcdaqadaqaaiaadIhadaWgaaWcbaGaamyA
aaqabaaakiaawIcacaGLPaaacaGGUaaaaa@3F03@
Biais de
l’estimateur fondé sur le modèle de Kuo
E
(
F
^
(
t
)
−
F
N
(
t
)
)
=
E
(
1
N
∑
i
∉
s
∑
j
∈
s
w
i
,
j
[
I
(
ε
j
≤
t
−
m
j
)
−
I
(
ε
i
≤
t
−
m
i
)
]
)
=
1
N
∑
i
∉
s
∑
j
∈
s
w
i
,
j
[
G
(
t
−
m
j
|
x
j
)
−
G
(
t
−
m
i
|
x
i
)
]
=
1
2
N
∑
i
∉
s
[
G
(
2,0
)
(
t
−
m
i
|
x
i
)
(
m
i
′
)
2
−
G
(
1,0
)
(
t
−
m
i
|
x
i
)
m
i
′′
−
2
G
(
1,1
)
(
t
−
m
i
|
x
i
)
m
i
′
+
G
(
0
,
2
)
(
t
−
m
i
|
x
i
)
]
∑
j
∈
s
w
i
,
j
(
x
j
−
x
i
)
2
+
o
(
λ
2
)
=
λ
2
N
−
n
N
μ
2
2
μ
0
∫
a
b
[
G
(
2,0
)
(
t
−
m
(
x
)
|
x
)
(
m
′
(
x
)
)
2
−
G
(
1,0
)
(
t
−
m
(
x
)
|
x
)
m
′′
(
x
)
−
2
G
(
1,1
)
(
t
−
m
(
x
)
|
x
)
m
′
(
x
)
+
G
(
0
,
2
)
(
t
−
m
(
x
)
|
x
)
]
h
s
¯
(
x
)
d
x
+
o
(
λ
2
)
.
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrFfpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaqbaeaabyGaaa
aabaGaamyramaabmaabaGabmOrayaajaWaaeWaaeaacaWG0baacaGL
OaGaayzkaaGaeyOeI0IaamOramaaBaaaleaacaWGobaabeaakmaabm
aabaGaamiDaaGaayjkaiaawMcaaaGaayjkaiaawMcaaaqaaiaai2da
caWGfbWaaeWaaeaadaWcaaqaaiaaigdaaeaacaWGobaaamaaqafabe
WcbaGaamyAaiabgMGiplaadohaaeqaniabggHiLdGcdaaeqbqaaiaa
dEhadaWgaaWcbaGaamyAaiaaiYcacaWGQbaabeaaaeaacaWGQbGaey
icI4Saam4Caaqab0GaeyyeIuoakmaadmaabaGaamysamaabmaabaGa
eqyTdu2aaSbaaSqaaiaadQgaaeqaaOGaeyizImQaamiDaiabgkHiTi
aad2gadaWgaaWcbaGaamOAaaqabaaakiaawIcacaGLPaaacqGHsisl
caWGjbWaaeWaaeaacqaH1oqzdaWgaaWcbaGaamyAaaqabaGccqGHKj
YOcaWG0bGaeyOeI0IaamyBamaaBaaaleaacaWGPbaabeaaaOGaayjk
aiaawMcaaaGaay5waiaaw2faaaGaayjkaiaawMcaaaqaaaqaaiaai2
dadaWcaaqaaiaaigdaaeaacaWGobaaamaaqafabeWcbaGaamyAaiab
gMGiplaadohaaeqaniabggHiLdGcdaaeqbqaaiaadEhadaWgaaWcba
GaamyAaiaaiYcacaWGQbaabeaaaeaacaWGQbGaeyicI4Saam4Caaqa
b0GaeyyeIuoakmaadmaabaGaam4ramaabmaabaWaaqGaaeaacaWG0b
GaeyOeI0IaamyBamaaBaaaleaacaWGQbaabeaaaOGaayjcSdGaamiE
amaaBaaaleaacaWGQbaabeaaaOGaayjkaiaawMcaaiabgkHiTiaadE
eadaqadaqaamaaeiaabaGaamiDaiabgkHiTiaad2gadaWgaaWcbaGa
amyAaaqabaaakiaawIa7aiaadIhadaWgaaWcbaGaamyAaaqabaaaki
aawIcacaGLPaaaaiaawUfacaGLDbaaaeaaaeaacaaI9aWaaSaaaeaa
caaIXaaabaGaaGOmaiaad6eaaaWaaabuaeqaleaacaWGPbGaeyycI8
Saam4Caaqab0GaeyyeIuoakmaadeaabaGaam4ramaaCaaaleqabaWa
aeWaaeaacaaIYaGaaGilaiaaicdaaiaawIcacaGLPaaaaaGcdaqada
qaamaaeiaabaGaamiDaiabgkHiTiaad2gadaWgaaWcbaGaamyAaaqa
baaakiaawIa7aiaadIhadaWgaaWcbaGaamyAaaqabaaakiaawIcaca
GLPaaadaqadaqaaiqad2gagaqbamaaBaaaleaacaWGPbaabeaaaOGa
ayjkaiaawMcaamaaCaaaleqabaGaaGOmaaaakiabgkHiTiaadEeada
ahaaWcbeqaamaabmaabaGaaGymaiaaiYcacaaIWaaacaGLOaGaayzk
aaaaaOWaaeWaaeaadaabcaqaaiaadshacqGHsislcaWGTbWaaSbaaS
qaaiaadMgaaeqaaaGccaGLiWoacaWG4bWaaSbaaSqaaiaadMgaaeqa
aaGccaGLOaGaayzkaaGabmyBayaagaWaaSbaaSqaaiaadMgaaeqaaa
GccaGLBbaaaeaaaeaacaaMe8UaaGjbVpaadiaabaGaeyOeI0IaaGOm
aiaadEeadaahaaWcbeqaamaabmaabaGaaGymaiaaiYcacaaIXaaaca
GLOaGaayzkaaaaaOWaaeWaaeaadaabcaqaaiaadshacqGHsislcaWG
TbWaaSbaaSqaaiaadMgaaeqaaaGccaGLiWoacaWG4bWaaSbaaSqaai
aadMgaaeqaaaGccaGLOaGaayzkaaGabmyBayaafaWaaSbaaSqaaiaa
dMgaaeqaaOGaey4kaSIaam4ramaaCaaaleqabaWaaeWaaeaacaaIWa
GaaiilaiaaikdaaiaawIcacaGLPaaaaaGcdaqadaqaamaaeiaabaGa
amiDaiabgkHiTiaad2gadaWgaaWcbaGaamyAaaqabaaakiaawIa7ai
aadIhadaWgaaWcbaGaamyAaaqabaaakiaawIcacaGLPaaaaiaaw2fa
amaaqafabaGaam4DamaaBaaaleaacaWGPbGaaGilaiaadQgaaeqaaO
WaaeWaaeaacaWG4bWaaSbaaSqaaiaadQgaaeqaaOGaeyOeI0IaamiE
amaaBaaaleaacaWGPbaabeaaaOGaayjkaiaawMcaamaaCaaaleqaba
GaaGOmaaaaaeaacaWGQbGaeyicI4Saam4Caaqab0GaeyyeIuoakiab
gUcaRiaad+gadaqadaqaaiabeU7aSnaaCaaaleqabaGaaGOmaaaaaO
GaayjkaiaawMcaaaqaaaqaaiaai2dacqaH7oaBdaahaaWcbeqaaiaa
ikdaaaGcdaWcaaqaaiaad6eacqGHsislcaWGUbaabaGaamOtaaaada
WcaaqaaiabeY7aTnaaBaaaleaacaaIYaaabeaaaOqaaiaaikdacqaH
8oqBdaWgaaWcbaGaaGimaaqabaaaaOWaa8qmaeqaleaacaWGHbaaba
GaamOyaaqdcqGHRiI8aOWaamqaaeaacaWGhbWaaWbaaSqabeaadaqa
daqaaiaaikdacaaISaGaaGimaaGaayjkaiaawMcaaaaakmaabmaaba
WaaqGaaeaacaWG0bGaeyOeI0IaamyBamaabmaabaGaamiEaaGaayjk
aiaawMcaaiaaykW7aiaawIa7aiaadIhaaiaawIcacaGLPaaadaqada
qaaiqad2gagaqbamaabmaabaGaamiEaaGaayjkaiaawMcaaaGaayjk
aiaawMcaamaaCaaaleqabaGaaGOmaaaakiabgkHiTiaadEeadaahaa
WcbeqaamaabmaabaGaaGymaiaaiYcacaaIWaaacaGLOaGaayzkaaaa
aOWaaeWaaeaadaabcaqaaiaadshacqGHsislcaWGTbWaaeWaaeaaca
WG4baacaGLOaGaayzkaaGaaGPaVdGaayjcSdGaamiEaaGaayjkaiaa
wMcaaiqad2gagaqbgaqbamaabmaabaGaamiEaaGaayjkaiaawMcaaa
Gaay5waaaabaaabaGaaGjbVlaaysW7daWacaqaaiabgkHiTiaaikda
caWGhbWaaWbaaSqabeaadaqadaqaaiaaigdacaaISaGaaGymaaGaay
jkaiaawMcaaaaakmaabmaabaWaaqGaaeaacaWG0bGaeyOeI0IaamyB
amaabmaabaGaamiEaaGaayjkaiaawMcaaiaaykW7aiaawIa7aiaadI
haaiaawIcacaGLPaaaceWGTbGbauaadaqadaqaaiaadIhaaiaawIca
caGLPaaacqGHRaWkcaWGhbWaaWbaaSqabeaadaqadaqaaiaaicdaca
GGSaGaaGOmaaGaayjkaiaawMcaaaaakmaabmaabaWaaqGaaeaacaWG
0bGaeyOeI0IaamyBamaabmaabaGaamiEaaGaayjkaiaawMcaaiaayk
W7aiaawIa7aiaadIhaaiaawIcacaGLPaaaaiaaw2faaiaadIgadaWg
aaWcbaGaaGPaVlqadohagaqeaaqabaGcdaqadaqaaiaadIhaaiaawI
cacaGLPaaacaWGKbGaamiEaiabgUcaRiaad+gadaqadaqaaiabeU7a
SnaaCaaaleqabaGaaGOmaaaaaOGaayjkaiaawMcaaiaai6caaaaaaa@71E0@
Biais de l’estimateur par la différence
généralisée de Kuo
Écrivons
F
˜
(
t
)
−
F
N
(
t
)
=
1
N
{
∑
i
∉
s
∑
j
∈
s
w
˜
i
,
j
[
I
(
ε
j
≤
t
−
m
j
)
−
I
(
ε
i
≤
t
−
m
i
)
]
+
∑
i
∈
s
(
1
−
1
π
i
)
∑
j
∈
s
w
˜
i
,
j
[
I
(
ε
j
≤
t
−
m
j
)
−
I
(
ε
i
≤
t
−
m
i
)
]
}
.
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrVeFfea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaafaqaaeGaca
aabaGabmOrayaaiaWaaeWaaeaacaWG0baacaGLOaGaayzkaaGaeyOe
I0IaamOramaaBaaaleaacaWGobaabeaakmaabmaabaGaamiDaaGaay
jkaiaawMcaaaqaaiaai2dadaWcaaqaaiaaigdaaeaacaWGobaaamaa
ceaabaWaaabuaeqaleaacaWGPbGaeyycI8Saam4Caaqab0GaeyyeIu
oakmaaqafabaGabm4DayaaiaWaaSbaaSqaaiaadMgacaaISaGaamOA
aaqabaaabaGaamOAaiabgIGiolaadohaaeqaniabggHiLdGcdaWada
qaaiaadMeadaqadaqaaiabew7aLnaaBaaaleaacaWGQbaabeaakiab
gsMiJkaadshacqGHsislcaWGTbWaaSbaaSqaaiaadQgaaeqaaaGcca
GLOaGaayzkaaGaeyOeI0IaamysamaabmaabaGaeqyTdu2aaSbaaSqa
aiaadMgaaeqaaOGaeyizImQaamiDaiabgkHiTiaad2gadaWgaaWcba
GaamyAaaqabaaakiaawIcacaGLPaaaaiaawUfacaGLDbaaaiaawUha
aaqaaaqaaiaaysW7caaMe8+aaiGaaeaacaaMe8UaaGjbVlaaysW7ca
aMe8UaaGjbVlaaysW7cqGHRaWkdaaeqbqabSqaaiaadMgacqGHiiIZ
caWGZbaabeqdcqGHris5aOWaaeWaaeaacaaIXaGaeyOeI0YaaSaaae
aacaaIXaaabaGaeqiWda3aaSbaaSqaaiaadMgaaeqaaaaaaOGaayjk
aiaawMcaaiaaysW7daaeqbqaaiqadEhagaacamaaBaaaleaacaWGPb
GaaGilaiaadQgaaeqaaaqaaiaadQgacqGHiiIZcaWGZbaabeqdcqGH
ris5aOWaamWaaeaacaWGjbWaaeWaaeaacqaH1oqzdaWgaaWcbaGaam
OAaaqabaGccqGHKjYOcaWG0bGaeyOeI0IaamyBamaaBaaaleaacaWG
QbaabeaaaOGaayjkaiaawMcaaiabgkHiTiaadMeadaqadaqaaiabew
7aLnaaBaaaleaacaWGPbaabeaakiabgsMiJkaadshacqGHsislcaWG
TbWaaSbaaSqaaiaadMgaaeqaaaGccaGLOaGaayzkaaaacaGLBbGaay
zxaaaacaGL9baacaaIUaaaaaaa@AADE@
Des étapes similaires à celles suivies
pour
F
^
(
t
)
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaaceWGgbGbaK
aadaqadaqaaiaadshaaiaawIcacaGLPaaaaaa@3B4E@
montrent que
E
(
F
˜
(
t
)
−
F
N
(
t
)
)
=
λ
2
N
−
n
N
μ
2
2
μ
0
∫
a
b
[
G
(
2,0
)
(
t
−
m
(
x
)
|
x
)
(
m
′
(
x
)
)
2
−
G
(
1,0
)
(
t
−
m
(
x
)
|
x
)
m
′′
(
x
)
−
2
G
(
1,1
)
(
t
−
m
(
x
)
|
x
)
m
′
(
x
)
+
G
(
0
,
2
)
(
t
−
m
(
x
)
|
x
)
]
h
(
x
)
d
x
+
o
(
λ
2
)
,
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrFfpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaafaqaaeGaca
aabaGaamyramaabmaabaGabmOrayaaiaWaaeWaaeaacaWG0baacaGL
OaGaayzkaaGaeyOeI0IaamOramaaBaaaleaacaWGobaabeaakmaabm
aabaGaamiDaaGaayjkaiaawMcaaaGaayjkaiaawMcaaaqaaiaai2da
cqaH7oaBdaahaaWcbeqaaiaaikdaaaGcdaWcaaqaaiaad6eacqGHsi
slcaWGUbaabaGaamOtaaaadaWcaaqaaiabeY7aTnaaBaaaleaacaaI
YaaabeaaaOqaaiaaikdacqaH8oqBdaWgaaWcbaGaaGimaaqabaaaaO
Waa8qmaeaadaWabaqaaiaadEeadaahaaWcbeqaamaabmaabaGaaGOm
aiaaiYcacaaIWaaacaGLOaGaayzkaaaaaOWaaeWaaeaadaabcaqaai
aadshacqGHsislcaWGTbWaaeWaaeaacaWG4baacaGLOaGaayzkaaGa
aGPaVdGaayjcSdGaamiEaaGaayjkaiaawMcaamaabmaabaGabmyBay
aafaWaaeWaaeaacaWG4baacaGLOaGaayzkaaaacaGLOaGaayzkaaWa
aWbaaSqabeaacaaIYaaaaOGaeyOeI0Iaam4ramaaCaaaleqabaWaae
WaaeaacaaIXaGaaGilaiaaicdaaiaawIcacaGLPaaaaaGcdaqadaqa
amaaeiaabaGaamiDaiabgkHiTiaad2gadaqadaqaaiaadIhaaiaawI
cacaGLPaaacaaMc8oacaGLiWoacaWG4baacaGLOaGaayzkaaGabmyB
ayaafyaafaWaaeWaaeaacaWG4baacaGLOaGaayzkaaaacaGLBbaaaS
qaaiaadggaaeaacaWGIbaaniabgUIiYdaakeaaaeaadaWacaqaaiaa
ysW7caaMe8UaaGjbVlaaysW7caaMe8UaaGjbVlaaysW7caaMe8UaaG
jbVlaaysW7caaMe8UaaGjbVlaaysW7caaMe8UaaGjbVlaaysW7caaM
e8UaaGjbVlaaysW7caaMe8UaeyOeI0IaaGOmaiaadEeadaahaaWcbe
qaamaabmaabaGaaGymaiaaiYcacaaIXaaacaGLOaGaayzkaaaaaOWa
aeWaaeaadaabcaqaaiaadshacqGHsislcaWGTbWaaeWaaeaacaWG4b
aacaGLOaGaayzkaaGaaGPaVdGaayjcSdGaamiEaaGaayjkaiaawMca
aiqad2gagaqbamaabmaabaGaamiEaaGaayjkaiaawMcaaiabgUcaRi
aadEeadaahaaWcbeqaamaabmaabaGaaGimaiaacYcacaaIYaaacaGL
OaGaayzkaaaaaOWaaeWaaeaadaabcaqaaiaadshacqGHsislcaWGTb
WaaeWaaeaacaWG4baacaGLOaGaayzkaaGaaGPaVdGaayjcSdGaamiE
aaGaayjkaiaawMcaaaGaayzxaaGaamiAamaabmaabaGaamiEaaGaay
jkaiaawMcaaiaadsgacaWG4bGaey4kaSIaam4BamaabmaabaGaeq4U
dW2aaWbaaSqabeaacaaIYaaaaaGccaGLOaGaayzkaaGaaiilaaaaaa
a@D090@
où
h
(
x
)
:=
h
s
¯
(
x
)
+
(
1
−
π
−
1
(
x
)
)
h
s
(
x
)
.
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWGObWaae
WaaeaacaWG4baacaGLOaGaayzkaaGaaGOoaiaai2dacaWGObWaaSba
aSqaaiaaykW7ceWGZbGbaebaaeqaaOWaaeWaaeaacaWG4baacaGLOa
GaayzkaaGaey4kaSYaaeWaaeaacaaIXaGaeyOeI0IaeqiWda3aaWba
aSqabeaacqGHsislcaaIXaaaaOWaaeWaaeaacaWG4baacaGLOaGaay
zkaaaacaGLOaGaayzkaaGaamiAamaaBaaaleaacaWGZbaabeaakmaa
bmaabaGaamiEaaGaayjkaiaawMcaaiaai6caaaa@52C0@
Variance de l’estimateur fondé sur le modèle de
Kuo
var
(
F
^
(
t
)
−
F
N
(
t
)
)
=
var
(
1
N
∑
i
∉
s
∑
j
∈
s
w
i
,
j
I
(
ε
j
≤
t
−
m
j
)
−
1
N
∑
i
∉
s
I
(
y
i
≤
t
)
)
=
1
N
2
∑
i
1
∉
s
∑
i
2
∉
s
∑
j
∈
s
w
i
1
,
j
w
i
2
,
j
[
G
(
t
−
m
j
|
x
j
)
−
G
2
(
t
−
m
j
|
x
j
)
]
+
1
N
2
∑
i
∉
s
[
G
(
t
−
m
i
|
x
i
)
−
G
2
(
t
−
m
i
|
x
i
)
]
=
A
1
+
A
2
,
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrFfpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaafaqaaeabca
aaaeaacaqG2bGaaeyyaiaabkhadaqadaqaaiqadAeagaqcamaabmaa
baGaamiDaaGaayjkaiaawMcaaiabgkHiTiaadAeadaWgaaWcbaGaam
OtaaqabaGcdaqadaqaaiaadshaaiaawIcacaGLPaaaaiaawIcacaGL
PaaaaeaacaaI9aGaaeODaiaabggacaqGYbWaaeWaaeaadaWcaaqaai
aaigdaaeaacaWGobaaamaaqafabeWcbaGaamyAaiabgMGiplaadoha
aeqaniabggHiLdGcdaaeqbqaaiaadEhadaWgaaWcbaGaamyAaiaaiY
cacaWGQbaabeaakiaadMeaaSqaaiaadQgacqGHiiIZcaWGZbaabeqd
cqGHris5aOWaaeWaaeaacqaH1oqzdaWgaaWcbaGaamOAaaqabaGccq
GHKjYOcaWG0bGaeyOeI0IaamyBamaaBaaaleaacaWGQbaabeaaaOGa
ayjkaiaawMcaaiabgkHiTmaalaaabaGaaGymaaqaaiaad6eaaaWaaa
buaeaacaWGjbWaaeWaaeaacaWG5bWaaSbaaSqaaiaadMgaaeqaaOGa
eyizImQaamiDaaGaayjkaiaawMcaaaWcbaGaamyAaiabgMGiplaado
haaeqaniabggHiLdaakiaawIcacaGLPaaaaeaaaeaacaaI9aWaaSaa
aeaacaaIXaaabaGaamOtamaaCaaaleqabaGaaGOmaaaaaaGcdaaeqb
qaamaaqafabaWaaabuaeaacaWG3bWaaSbaaSqaaiaadMgadaWgaaad
baGaaGymaaqabaWccaaISaGaamOAaaqabaGccaWG3bWaaSbaaSqaai
aadMgadaWgaaadbaGaaGOmaaqabaWccaaISaGaamOAaaqabaaabaGa
amOAaiabgIGiolaadohaaeqaniabggHiLdaaleaacaWGPbWaaSbaaW
qaaiaaikdaaeqaaSGaeyycI8Saam4Caaqab0GaeyyeIuoaaSqaaiaa
dMgadaWgaaadbaGaaGymaaqabaWccqGHjiYZcaWGZbaabeqdcqGHri
s5aOWaamWaaeaacaWGhbWaaeWaaeaadaabcaqaaiaadshacqGHsisl
caWGTbWaaSbaaSqaaiaadQgaaeqaaaGccaGLiWoacaaMc8UaamiEam
aaBaaaleaacaWGQbaabeaaaOGaayjkaiaawMcaaiabgkHiTiaadEea
daahaaWcbeqaaiaaikdaaaGcdaqadaqaamaaeiaabaGaamiDaiabgk
HiTiaad2gadaWgaaWcbaGaamOAaaqabaaakiaawIa7aiaaykW7caWG
4bWaaSbaaSqaaiaadQgaaeqaaaGccaGLOaGaayzkaaaacaGLBbGaay
zxaaaabaaabaGaaGjbVlaaysW7cqGHRaWkdaWcaaqaaiaaigdaaeaa
caWGobWaaWbaaSqabeaacaaIYaaaaaaakmaaqafabeWcbaGaamyAai
abgMGiplaadohaaeqaniabggHiLdGcdaWadaqaaiaadEeadaqadaqa
amaaeiaabaGaamiDaiabgkHiTiaad2gadaWgaaWcbaGaamyAaaqaba
aakiaawIa7aiaaykW7caWG4bWaaSbaaSqaaiaadMgaaeqaaaGccaGL
OaGaayzkaaGaeyOeI0Iaam4ramaaCaaaleqabaGaaGOmaaaakmaabm
aabaWaaqGaaeaacaWG0bGaeyOeI0IaamyBamaaBaaaleaacaWGPbaa
beaaaOGaayjcSdGaaGPaVlaadIhadaWgaaWcbaGaamyAaaqabaaaki
aawIcacaGLPaaaaiaawUfacaGLDbaaaeaaaeaacaaI9aGaamyqamaa
BaaaleaacaaIXaaabeaakiabgUcaRiaadgeadaWgaaWcbaGaaGOmaa
qabaGccaaISaaaaaaa@DC0E@
où
A
1
:=
1
N
2
∑
i
1
∉
s
∑
i
2
∉
s
∑
j
∈
s
w
i
1
,
j
w
i
2
,
j
[
G
(
t
−
m
j
|
x
j
)
−
G
2
(
t
−
m
j
|
x
j
)
]
=
1
N
2
∑
j
∈
s
[
G
(
t
−
m
j
|
x
j
)
−
G
2
(
t
−
m
j
|
x
j
)
]
(
∑
i
∉
s
w
i
,
j
)
2
=
1
n
(
N
−
n
N
)
2
∫
a
b
[
G
(
t
−
m
(
x
)
|
x
)
−
G
2
(
t
−
m
(
x
)
|
x
)
]
[
h
s
¯
(
x
)
/
h
s
(
x
)
]
h
s
¯
(
x
)
d
x
+
O
(
(
n
λ
)
−
1
α
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaafaqaaeabca
aaaeaacaWGbbWaaSbaaSqaaiaaigdaaeqaaaGcbaGaaGOoaiaai2da
daWcaaqaaiaaigdaaeaacaWGobWaaWbaaSqabeaacaaIYaaaaaaakm
aaqafabaWaaabuaeaadaaeqbqaaiaadEhadaWgaaWcbaGaamyAamaa
BaaameaacaaIXaaabeaaliaaiYcacaWGQbaabeaakiaadEhadaWgaa
WcbaGaamyAamaaBaaameaacaaIYaaabeaaliaaiYcacaWGQbaabeaa
aeaacaWGQbGaeyicI4Saam4Caaqab0GaeyyeIuoaaSqaaiaadMgada
WgaaadbaGaaGOmaaqabaWccqGHjiYZcaWGZbaabeqdcqGHris5aaWc
baGaamyAamaaBaaameaacaaIXaaabeaaliabgMGiplaadohaaeqani
abggHiLdGcdaWadaqaaiaadEeadaqadaqaamaaeiaabaGaamiDaiab
gkHiTiaad2gadaWgaaWcbaGaamOAaaqabaaakiaawIa7aiaaykW7ca
WG4bWaaSbaaSqaaiaadQgaaeqaaaGccaGLOaGaayzkaaGaeyOeI0Ia
am4ramaaCaaaleqabaGaaGOmaaaakmaabmaabaWaaqGaaeaacaWG0b
GaeyOeI0IaamyBamaaBaaaleaacaWGQbaabeaaaOGaayjcSdGaaGPa
VlaadIhadaWgaaWcbaGaamOAaaqabaaakiaawIcacaGLPaaaaiaawU
facaGLDbaaaeaaaeaacaaI9aWaaSaaaeaacaaIXaaabaGaamOtamaa
CaaaleqabaGaaGOmaaaaaaGcdaaeqbqabSqaaiaadQgacqGHiiIZca
WGZbaabeqdcqGHris5aOWaamWaaeaacaWGhbWaaeWaaeaadaabcaqa
aiaadshacqGHsislcaWGTbWaaSbaaSqaaiaadQgaaeqaaaGccaGLiW
oacaaMc8UaamiEamaaBaaaleaacaWGQbaabeaaaOGaayjkaiaawMca
aiabgkHiTiaadEeadaahaaWcbeqaaiaaikdaaaGcdaqadaqaamaaei
aabaGaamiDaiabgkHiTiaad2gadaWgaaWcbaGaamOAaaqabaaakiaa
wIa7aiaaykW7caWG4bWaaSbaaSqaaiaadQgaaeqaaaGccaGLOaGaay
zkaaaacaGLBbGaayzxaaWaaeWaaeaadaaeqbqabSqaaiaadMgacqGH
jiYZcaWGZbaabeqdcqGHris5aOGaam4DamaaBaaaleaacaWGPbGaaG
ilaiaadQgaaeqaaaGccaGLOaGaayzkaaWaaWbaaSqabeaacaaIYaaa
aaGcbaaabaGaaGypamaalaaabaGaaGymaaqaaiaad6gaaaWaaeWaae
aadaWcaaqaaiaad6eacqGHsislcaWGUbaabaGaamOtaaaaaiaawIca
caGLPaaadaahaaWcbeqaaiaaikdaaaGcdaWdXaqabSqaaiaadggaae
aacaWGIbaaniabgUIiYdGcdaWadaqaaiaadEeadaqadaqaamaaeiaa
baGaamiDaiabgkHiTiaad2gadaqadaqaaiaadIhaaiaawIcacaGLPa
aacaaMc8oacaGLiWoacaaMc8UaamiEaaGaayjkaiaawMcaaiabgkHi
TiaadEeadaahaaWcbeqaaiaaikdaaaGcdaqadaqaamaaeiaabaGaam
iDaiabgkHiTiaad2gadaqadaqaaiaadIhaaiaawIcacaGLPaaacaaM
c8oacaGLiWoacaaMc8UaamiEaaGaayjkaiaawMcaaaGaay5waiaaw2
faamaadmaabaWaaSGbaeaacaWGObWaaSbaaSqaaiaaykW7ceWGZbGb
aebaaeqaaOWaaeWaaeaacaWG4baacaGLOaGaayzkaaaabaGaamiAam
aaBaaaleaacaWGZbaabeaakmaabmaabaGaamiEaaGaayjkaiaawMca
aaaaaiaawUfacaGLDbaacaWGObWaaSbaaSqaaiaaykW7ceWGZbGbae
baaeqaaOWaaeWaaeaacaWG4baacaGLOaGaayzkaaGaamizaiaadIha
aeaaaeaacaaMe8UaaGjbVlabgUcaRiaad+eadaqadaqaamaabmaaba
GaamOBaiabeU7aSbGaayjkaiaawMcaamaaCaaaleqabaGaeyOeI0Ia
aGymaaaakiabeg7aHbGaayjkaiaawMcaaaaaaaa@F2D5@
et
A
2
:=
1
N
2
∑
i
∉
s
[
G
(
t
−
m
i
|
x
i
)
−
G
2
(
t
−
m
i
|
x
i
)
]
=
1
N
−
n
(
N
−
n
N
)
2
∫
a
b
[
G
(
t
−
m
(
x
)
|
x
)
−
G
2
(
t
−
m
(
x
)
|
x
)
]
h
s
¯
(
x
)
d
x
+
O
(
n
−
1
α
)
.
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaafaqaaeGaca
aabaGaamyqamaaBaaaleaacaaIYaaabeaaaOqaaiaaiQdacaaI9aWa
aSaaaeaacaaIXaaabaGaamOtamaaCaaaleqabaGaaGOmaaaaaaGcda
aeqbqabSqaaiaadMgacqGHjiYZcaWGZbaabeqdcqGHris5aOWaamWa
aeaacaWGhbWaaeWaaeaadaabcaqaaiaadshacqGHsislcaWGTbWaaS
baaSqaaiaadMgaaeqaaaGccaGLiWoacaaMc8UaamiEamaaBaaaleaa
caWGPbaabeaaaOGaayjkaiaawMcaaiabgkHiTiaadEeadaahaaWcbe
qaaiaaikdaaaGcdaqadaqaamaaeiaabaGaamiDaiabgkHiTiaad2ga
daWgaaWcbaGaamyAaaqabaaakiaawIa7aiaaykW7caWG4bWaaSbaaS
qaaiaadMgaaeqaaaGccaGLOaGaayzkaaaacaGLBbGaayzxaaaabaaa
baGaaGypamaalaaabaGaaGymaaqaaiaad6eacqGHsislcaWGUbaaam
aabmaabaWaaSaaaeaacaWGobGaeyOeI0IaamOBaaqaaiaad6eaaaaa
caGLOaGaayzkaaWaaWbaaSqabeaacaaIYaaaaOWaa8qmaeqaleaaca
WGHbaabaGaamOyaaqdcqGHRiI8aOWaamWaaeaacaWGhbWaaeWaaeaa
daabcaqaaiaadshacqGHsislcaWGTbWaaeWaaeaacaWG4baacaGLOa
GaayzkaaGaaGPaVdGaayjcSdGaaGPaVlaadIhaaiaawIcacaGLPaaa
cqGHsislcaWGhbWaaWbaaSqabeaacaaIYaaaaOWaaeWaaeaadaabca
qaaiaadshacqGHsislcaWGTbWaaeWaaeaacaWG4baacaGLOaGaayzk
aaGaaGPaVdGaayjcSdGaaGPaVlaadIhaaiaawIcacaGLPaaaaiaawU
facaGLDbaacaWGObWaaSbaaSqaaiaaykW7ceWGZbGbaebaaeqaaOWa
aeWaaeaacaWG4baacaGLOaGaayzkaaGaamizaiaadIhacqGHRaWkca
WGpbWaaeWaaeaacaWGUbWaaWbaaSqabeaacqGHsislcaaIXaaaaOGa
eqySdegacaGLOaGaayzkaaGaaGOlaaaaaaa@9BD9@
Donc,
var
(
F
^
(
t
)
−
F
N
(
t
)
)
=
1
n
(
N
−
n
N
)
2
∫
a
b
[
G
(
t
−
m
(
x
)
|
x
)
−
G
2
(
t
−
m
(
x
)
|
x
)
]
[
h
s
¯
(
x
)
/
h
s
(
x
)
]
h
s
¯
(
x
)
d
x
+
1
N
−
n
(
N
−
n
N
)
2
∫
a
b
[
G
(
t
−
m
(
x
)
|
x
)
−
G
2
(
t
−
m
(
x
)
|
x
)
]
h
s
¯
(
x
)
d
x
+
O
(
(
n
λ
)
−
1
α
)
.
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaafaqaaeGaca
aabaGaaeODaiaabggacaqGYbWaaeWaaeaaceWGgbGbaKaadaqadaqa
aiaadshaaiaawIcacaGLPaaacqGHsislcaWGgbWaaSbaaSqaaiaad6
eaaeqaaOWaaeWaaeaacaWG0baacaGLOaGaayzkaaaacaGLOaGaayzk
aaaabaGaeyypa0ZaaSaaaeaacaaIXaaabaGaamOBaaaadaqadaqaam
aalaaabaGaamOtaiabgkHiTiaad6gaaeaacaWGobaaaaGaayjkaiaa
wMcaamaaCaaaleqabaGaaGOmaaaakmaapedabeWcbaGaamyyaaqaai
aadkgaa0Gaey4kIipakmaadmaabaGaam4ramaabmaabaWaaqGaaeaa
caWG0bGaeyOeI0IaamyBamaabmaabaGaamiEaaGaayjkaiaawMcaai
aaykW7aiaawIa7aiaaysW7caWG4baacaGLOaGaayzkaaGaeyOeI0Ia
am4ramaaCaaaleqabaGaaGOmaaaakmaabmaabaWaaqGaaeaacaWG0b
GaeyOeI0IaamyBamaabmaabaGaamiEaaGaayjkaiaawMcaaiaaykW7
aiaawIa7aiaaysW7caWG4baacaGLOaGaayzkaaaacaGLBbGaayzxaa
WaamWaaeaadaWcgaqaaiaadIgadaWgaaWcbaGaaGPaVlqadohagaqe
aaqabaGcdaqadaqaaiaadIhaaiaawIcacaGLPaaaaeaacaWGObWaaS
baaSqaaiaadohaaeqaaOWaaeWaaeaacaWG4baacaGLOaGaayzkaaaa
aaGaay5waiaaw2faaiaadIgadaWgaaWcbaGaaGPaVlqadohagaqeaa
qabaGcdaqadaqaaiaadIhaaiaawIcacaGLPaaacaWGKbGaamiEaaqa
aaqaaiabgUcaRmaalaaabaGaaGymaaqaaiaad6eacqGHsislcaWGUb
aaamaabmaabaWaaSaaaeaacaWGobGaeyOeI0IaamOBaaqaaiaad6ea
aaaacaGLOaGaayzkaaWaaWbaaSqabeaacaaIYaaaaOWaa8qmaeqale
aacaWGHbaabaGaamOyaaqdcqGHRiI8aOWaamWaaeaacaWGhbWaaeWa
aeaadaabcaqaaiaadshacqGHsislcaWGTbWaaeWaaeaacaWG4baaca
GLOaGaayzkaaGaaGPaVdGaayjcSdGaaGjbVlaadIhaaiaawIcacaGL
PaaacqGHsislcaWGhbWaaWbaaSqabeaacaaIYaaaaOWaaeWaaeaada
abcaqaaiaadshacqGHsislcaWGTbWaaeWaaeaacaWG4baacaGLOaGa
ayzkaaGaaGPaVdGaayjcSdGaaGjbVlaadIhaaiaawIcacaGLPaaaai
aawUfacaGLDbaacaWGObWaaSbaaSqaaiaaykW7ceWGZbGbaebaaeqa
aOWaaeWaaeaacaWG4baacaGLOaGaayzkaaGaamizaiaadIhacqGHRa
WkcaWGpbWaaeWaaeaadaqadaqaaiaad6gacqaH7oaBaiaawIcacaGL
PaaadaahaaWcbeqaaiabgkHiTiaaigdaaaGccqaHXoqyaiaawIcaca
GLPaaacaaIUaaaaaaa@C646@
Variance de l’estimateur par la différence
généralisée de Kuo
Notons que,
F
˜
(
t
)
−
F
N
(
t
)
=
1
N
{
∑
j
∈
s
I
(
y
j
≤
t
)
[
∑
i
∉
s
w
˜
i
,
j
−
∑
i
∈
s
w
˜
i
,
j
(
π
i
−
1
−
1
)
+
(
π
j
−
1
−
1
)
]
−
∑
i
∉
s
I
(
y
i
≤
t
)
}
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaaceWGgbGbaG
aadaqadaqaaiaadshaaiaawIcacaGLPaaacqGHsislcaWGgbWaaSba
aSqaaiaad6eaaeqaaOWaaeWaaeaacaWG0baacaGLOaGaayzkaaGaaG
ypamaalaaabaGaaGymaaqaaiaad6eaaaWaaiWaaeaadaaeqbqaaiaa
dMeadaqadaqaaiaadMhadaWgaaWcbaGaamOAaaqabaGccqGHKjYOca
WG0baacaGLOaGaayzkaaaaleaacaWGQbGaeyicI4Saam4Caaqab0Ga
eyyeIuoakmaadmaabaWaaabuaeaaceWG3bGbaGaadaWgaaWcbaGaam
yAaiaaiYcacaWGQbaabeaaaeaacaWGPbGaeyycI8Saam4Caaqab0Ga
eyyeIuoakiabgkHiTmaaqafabaGabm4DayaaiaWaaSbaaSqaaiaadM
gacaaISaGaamOAaaqabaaabaGaamyAaiabgIGiolaadohaaeqaniab
ggHiLdGcdaqadaqaaiabec8aWnaaDaaaleaacaWGPbaabaGaeyOeI0
IaaGymaaaakiabgkHiTiaaigdaaiaawIcacaGLPaaacqGHRaWkdaqa
daqaaiabec8aWnaaDaaaleaacaWGQbaabaGaeyOeI0IaaGymaaaaki
abgkHiTiaaigdaaiaawIcacaGLPaaaaiaawUfacaGLDbaacqGHsisl
daaeqbqaaiaadMeadaqadaqaaiaadMhadaWgaaWcbaGaamyAaaqaba
GccqGHKjYOcaWG0baacaGLOaGaayzkaaaaleaacaWGPbGaeyycI8Sa
am4Caaqab0GaeyyeIuoaaOGaay5Eaiaaw2haaaaa@8578@
de sorte que
var
(
F
˜
(
t
)
−
F
N
(
t
)
)
=
var
(
1
N
∑
j
∈
s
I
(
y
j
≤
t
)
[
∑
i
∉
s
w
˜
i
,
j
+
(
π
j
−
1
−
1
)
−
∑
i
∈
s
w
˜
i
,
j
(
π
i
−
1
−
1
)
]
)
+
var
(
1
N
∑
i
∉
s
I
(
y
i
≤
t
)
)
=
B
1
+
A
2
,
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaafaqaaeWaca
aabaGaaeODaiaabggacaqGYbWaaeWaaeaaceWGgbGbaGaadaqadaqa
aiaadshaaiaawIcacaGLPaaacqGHsislcaWGgbWaaSbaaSqaaiaad6
eaaeqaaOWaaeWaaeaacaWG0baacaGLOaGaayzkaaaacaGLOaGaayzk
aaaabaGaaGypaiaabAhacaqGHbGaaeOCamaabmaabaWaaSaaaeaaca
aIXaaabaGaamOtaaaadaaeqbqaaiaadMeadaqadaqaaiaadMhadaWg
aaWcbaGaamOAaaqabaGccqGHKjYOcaWG0baacaGLOaGaayzkaaaale
aacaWGQbGaeyicI4Saam4Caaqab0GaeyyeIuoakmaadmaabaWaaabu
aeaaceWG3bGbaGaadaWgaaWcbaGaamyAaiaaiYcacaWGQbaabeaaae
aacaWGPbGaeyycI8Saam4Caaqab0GaeyyeIuoakiabgUcaRmaabmaa
baGaeqiWda3aa0baaSqaaiaadQgaaeaacqGHsislcaaIXaaaaOGaey
OeI0IaaGymaaGaayjkaiaawMcaaiabgkHiTmaaqafabaGabm4Dayaa
iaWaaSbaaSqaaiaadMgacaaISaGaamOAaaqabaaabaGaamyAaiabgI
GiolaadohaaeqaniabggHiLdGcdaqadaqaaiabec8aWnaaDaaaleaa
caWGPbaabaGaeyOeI0IaaGymaaaakiabgkHiTiaaigdaaiaawIcaca
GLPaaaaiaawUfacaGLDbaaaiaawIcacaGLPaaaaeaaaeaacaaMe8Ua
aGjbVlabgUcaRiaabAhacaqGHbGaaeOCamaabmaabaWaaSaaaeaaca
aIXaaabaGaamOtaaaadaaeqbqaaiaadMeadaqadaqaaiaadMhadaWg
aaWcbaGaamyAaaqabaGccqGHKjYOcaWG0baacaGLOaGaayzkaaaale
aacaWGPbGaeyycI8Saam4Caaqab0GaeyyeIuoaaOGaayjkaiaawMca
aaqaaaqaaiaai2dacaWGcbWaaSbaaSqaaiaaigdaaeqaaOGaey4kaS
IaamyqamaaBaaaleaacaaIYaaabeaakiaaiYcaaaaaaa@9AE6@
où le terme
A
2
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWGbbWaaS
baaSqaaiaaikdaaeqaaaaa@399F@
est le même que dans la variance
de
F
^
(
t
)
,
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaaceWGgbGbaK
aadaqadaqaaiaadshaaiaawIcacaGLPaaacaGGSaaaaa@3BFE@
et où
B
1
:=
var
(
1
N
∑
j
∈
s
I
(
y
j
≤
t
)
[
∑
i
∉
s
w
˜
i
,
j
+
(
π
j
−
1
−
1
)
−
∑
i
∈
s
w
˜
i
,
j
(
π
i
−
1
−
1
)
]
)
=
1
N
2
∑
j
∈
s
[
G
(
t
−
m
j
|
x
j
)
−
G
2
(
t
−
m
j
|
x
j
)
]
[
∑
i
∉
s
w
˜
i
,
j
+
(
π
j
−
1
−
1
)
−
∑
i
∈
s
w
˜
i
,
j
(
π
i
−
1
−
1
)
]
2
=
1
N
2
∑
j
∈
s
[
G
(
t
−
m
j
|
x
j
)
−
G
2
(
t
−
m
j
|
x
j
)
]
[
∑
i
∉
s
w
˜
i
,
j
+
(
π
j
−
1
−
1
)
(
1
−
∑
i
∈
s
w
˜
i
,
j
)
]
2
+
O
(
λ
n
−
1
)
=
1
n
(
N
−
n
N
)
2
∫
a
b
[
G
(
t
−
m
(
x
)
|
x
)
−
G
2
(
t
−
m
(
x
)
|
x
)
]
[
h
s
¯
(
x
)
/
h
s
(
x
)
]
h
s
¯
(
x
)
d
x
+
O
(
(
n
λ
)
−
1
α
+
λ
n
−
1
)
=
A
1
+
O
(
(
n
λ
)
−
1
α
+
λ
n
−
1
)
.
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaafaqaaeGbca
aaaeaacaWGcbWaaSbaaSqaaiaaigdaaeqaaaGcbaGaaGOoaiaai2da
caqG2bGaaeyyaiaabkhadaqadaqaamaalaaabaGaaGymaaqaaiaad6
eaaaWaaabuaeaacaWGjbWaaeWaaeaacaWG5bWaaSbaaSqaaiaadQga
aeqaaOGaeyizImQaamiDaaGaayjkaiaawMcaaaWcbaGaamOAaiabgI
GiolaadohaaeqaniabggHiLdGcdaWadaqaamaaqafabaGabm4Dayaa
iaWaaSbaaSqaaiaadMgacaaISaGaamOAaaqabaaabaGaamyAaiabgM
GiplaadohaaeqaniabggHiLdGccqGHRaWkdaqadaqaaiabec8aWnaa
DaaaleaacaWGQbaabaGaeyOeI0IaaGymaaaakiabgkHiTiaaigdaai
aawIcacaGLPaaacqGHsisldaaeqbqaaiqadEhagaacamaaBaaaleaa
caWGPbGaaGilaiaadQgaaeqaaaqaaiaadMgacqGHiiIZcaWGZbaabe
qdcqGHris5aOWaaeWaaeaacqaHapaCdaqhaaWcbaGaamyAaaqaaiab
gkHiTiaaigdaaaGccqGHsislcaaIXaaacaGLOaGaayzkaaaacaGLBb
GaayzxaaaacaGLOaGaayzkaaaabaaabaGaaGypamaalaaabaGaaGym
aaqaaiaad6eadaahaaWcbeqaaiaaikdaaaaaaOWaaabuaeqaleaaca
WGQbGaeyicI4Saam4Caaqab0GaeyyeIuoakmaadmaabaGaam4ramaa
bmaabaWaaqGaaeaacaWG0bGaeyOeI0IaamyBamaaBaaaleaacaWGQb
aabeaaaOGaayjcSdGaaGjbVlaadIhadaWgaaWcbaGaamOAaaqabaaa
kiaawIcacaGLPaaacqGHsislcaWGhbWaaWbaaSqabeaacaaIYaaaaO
WaaeWaaeaadaabcaqaaiaadshacqGHsislcaWGTbWaaSbaaSqaaiaa
dQgaaeqaaaGccaGLiWoacaaMe8UaamiEamaaBaaaleaacaWGQbaabe
aaaOGaayjkaiaawMcaaaGaay5waiaaw2faamaadmaabaWaaabuaeaa
ceWG3bGbaGaadaWgaaWcbaGaamyAaiaaiYcacaWGQbaabeaaaeaaca
WGPbGaeyycI8Saam4Caaqab0GaeyyeIuoakiabgUcaRmaabmaabaGa
eqiWda3aa0baaSqaaiaadQgaaeaacqGHsislcaaIXaaaaOGaeyOeI0
IaaGymaaGaayjkaiaawMcaaiabgkHiTmaaqafabaGabm4DayaaiaWa
aSbaaSqaaiaadMgacaaISaGaamOAaaqabaaabaGaamyAaiabgIGiol
aadohaaeqaniabggHiLdGcdaqadaqaaiabec8aWnaaDaaaleaacaWG
PbaabaGaeyOeI0IaaGymaaaakiabgkHiTiaaigdaaiaawIcacaGLPa
aaaiaawUfacaGLDbaadaahaaWcbeqaaiaaikdaaaaakeaaaeaacaaI
9aWaaSaaaeaacaaIXaaabaGaamOtamaaCaaaleqabaGaaGOmaaaaaa
GcdaaeqbqabSqaaiaadQgacqGHiiIZcaWGZbaabeqdcqGHris5aOWa
amWaaeaacaWGhbWaaeWaaeaadaabcaqaaiaadshacqGHsislcaWGTb
WaaSbaaSqaaiaadQgaaeqaaaGccaGLiWoacaaMe8UaamiEamaaBaaa
leaacaWGQbaabeaaaOGaayjkaiaawMcaaiabgkHiTiaadEeadaahaa
WcbeqaaiaaikdaaaGcdaqadaqaamaaeiaabaGaamiDaiabgkHiTiaa
d2gadaWgaaWcbaGaamOAaaqabaaakiaawIa7aiaaysW7caWG4bWaaS
baaSqaaiaadQgaaeqaaaGccaGLOaGaayzkaaaacaGLBbGaayzxaaWa
amWaaeaadaaeqbqaaiqadEhagaacamaaBaaaleaacaWGPbGaaGilai
aadQgaaeqaaaqaaiaadMgacqGHjiYZcaWGZbaabeqdcqGHris5aOGa
ey4kaSYaaeWaaeaacqaHapaCdaqhaaWcbaGaamOAaaqaaiabgkHiTi
aaigdaaaGccqGHsislcaaIXaaacaGLOaGaayzkaaWaaeWaaeaacaaI
XaGaeyOeI0YaaabuaeaaceWG3bGbaGaadaWgaaWcbaGaamyAaiaaiY
cacaWGQbaabeaaaeaacaWGPbGaeyicI4Saam4Caaqab0GaeyyeIuoa
aOGaayjkaiaawMcaaaGaay5waiaaw2faamaaCaaaleqabaGaaGOmaa
aakiabgUcaRiaad+eadaqadaqaaiabeU7aSjaad6gadaahaaWcbeqa
aiabgkHiTiaaigdaaaaakiaawIcacaGLPaaaaeaaaeaacaaI9aWaaS
aaaeaacaaIXaaabaGaamOBaaaadaqadaqaamaalaaabaGaamOtaiab
gkHiTiaad6gaaeaacaWGobaaaaGaayjkaiaawMcaamaaCaaaleqaba
GaaGOmaaaakmaapedabeWcbaGaamyyaaqaaiaadkgaa0Gaey4kIipa
kmaadmaabaGaam4ramaabmaabaWaaqGaaeaacaWG0bGaeyOeI0Iaam
yBamaabmaabaGaamiEaaGaayjkaiaawMcaaiaaykW7aiaawIa7aiaa
ysW7caWG4baacaGLOaGaayzkaaGaeyOeI0Iaam4ramaaCaaaleqaba
GaaGOmaaaakmaabmaabaWaaqGaaeaacaWG0bGaeyOeI0IaamyBamaa
bmaabaGaamiEaaGaayjkaiaawMcaaiaaykW7aiaawIa7aiaaysW7ca
WG4baacaGLOaGaayzkaaaacaGLBbGaayzxaaWaamWaaeaadaWcgaqa
aiaadIgadaWgaaWcbaGaaGPaVlqadohagaqeaaqabaGcdaqadaqaai
aadIhaaiaawIcacaGLPaaaaeaacaWGObWaaSbaaSqaaiaadohaaeqa
aOWaaeWaaeaacaWG4baacaGLOaGaayzkaaaaaaGaay5waiaaw2faai
aadIgadaWgaaWcbaGaaGPaVlqadohagaqeaaqabaGcdaqadaqaaiaa
dIhaaiaawIcacaGLPaaacaWGKbGaamiEaaqaaaqaaiaaysW7caaMe8
Uaey4kaSIaam4tamaabmaabaWaaeWaaeaacaWGUbGaeq4UdWgacaGL
OaGaayzkaaWaaWbaaSqabeaacqGHsislcaaIXaaaaOGaeqySdeMaey
4kaSIaeq4UdWMaamOBamaaCaaaleqabaGaeyOeI0IaaGymaaaaaOGa
ayjkaiaawMcaaaqaaaqaaiaai2dacaWGbbWaaSbaaSqaaiaaigdaae
qaaOGaey4kaSIaam4tamaabmaabaWaaeWaaeaacaWGUbGaeq4UdWga
caGLOaGaayzkaaWaaWbaaSqabeaacqGHsislcaaIXaaaaOGaeqySde
Maey4kaSIaeq4UdWMaamOBamaaCaaaleqabaGaeyOeI0IaaGymaaaa
aOGaayjkaiaawMcaaiaai6caaaaaaa@7306@
Donc,
var
(
F
˜
(
t
)
−
F
N
(
t
)
)
=
var
(
F
^
(
t
)
−
F
N
(
t
)
)
+
O
(
(
n
λ
)
−
1
α
+
λ
n
−
1
)
.
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaqG2bGaae
yyaiaabkhadaqadaqaaiqadAeagaacamaabmaabaGaamiDaaGaayjk
aiaawMcaaiabgkHiTiaadAeadaWgaaWcbaGaamOtaaqabaGcdaqada
qaaiaadshaaiaawIcacaGLPaaaaiaawIcacaGLPaaacaaI9aGaaeOD
aiaabggacaqGYbWaaeWaaeaaceWGgbGbaKaadaqadaqaaiaadshaai
aawIcacaGLPaaacqGHsislcaWGgbWaaSbaaSqaaiaad6eaaeqaaOWa
aeWaaeaacaWG0baacaGLOaGaayzkaaaacaGLOaGaayzkaaGaey4kaS
Iaam4tamaabmaabaWaaeWaaeaacaWGUbGaeq4UdWgacaGLOaGaayzk
aaWaaWbaaSqabeaacqGHsislcaaIXaaaaOGaeqySdeMaey4kaSIaeq
4UdWMaamOBamaaCaaaleqabaGaeyOeI0IaaGymaaaaaOGaayjkaiaa
wMcaaiaai6caaaa@63B9@
Biais de l’estimateur fondé sur le modèle avec
valeurs prédites modifiées
Soit
m
^
^
i
:=
∑
k
∈
s
w
i
,
k
m
k
,
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaaceWGTbGbaK
GbaKaadaWgaaWcbaGaamyAaaqabaGccaaI6aGaaGypamaaqababeWc
baGaam4AaiabgIGiolaadohaaeqaniabggHiLdGccaWG3bWaaSbaaS
qaaiaadMgacaaISaGaam4AaaqabaGccaWGTbWaaSbaaSqaaiaadUga
aeqaaOGaaiilaaaa@4799@
c
i
,
j
:=
1
−
w
j
,
j
+
w
i
,
j
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWGJbWaaS
baaSqaaiaadMgacaaISaGaamOAaaqabaGccaaI6aGaaGypaiaaigda
cqGHsislcaWG3bWaaSbaaSqaaiaadQgacaaISaGaamOAaaqabaGccq
GHRaWkcaWG3bWaaSbaaSqaaiaadMgacaaISaGaamOAaaqabaaaaa@4738@
et
d
i
,
j
:=
1
c
i
,
j
[
(
1
−
c
i
,
j
)
(
t
−
m
i
)
+
(
m
^
^
j
−
m
j
)
−
(
m
^
^
i
−
m
i
)
+
∑
k
∈
s
,
k
≠
j
(
w
j
,
k
−
w
i
,
k
)
ε
k
]
.
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWGKbWaaS
baaSqaaiaadMgacaaISaGaamOAaaqabaGccaaI6aGaaGypamaalaaa
baGaaGymaaqaaiaadogadaWgaaWcbaGaamyAaiaaiYcacaWGQbaabe
aaaaGcdaWadaqaamaabmaabaGaaGymaiabgkHiTiaadogadaWgaaWc
baGaamyAaiaaiYcacaWGQbaabeaaaOGaayjkaiaawMcaamaabmaaba
GaamiDaiabgkHiTiaad2gadaWgaaWcbaGaamyAaaqabaaakiaawIca
caGLPaaacqGHRaWkdaqadaqaaiqad2gagaqcgaqcamaaBaaaleaaca
WGQbaabeaakiabgkHiTiaad2gadaWgaaWcbaGaamOAaaqabaaakiaa
wIcacaGLPaaacqGHsisldaqadaqaaiqad2gagaqcgaqcamaaBaaale
aacaWGPbaabeaakiabgkHiTiaad2gadaWgaaWcbaGaamyAaaqabaaa
kiaawIcacaGLPaaacqGHRaWkdaaeqbqabSqaaiaadUgacqGHiiIZca
WGZbGaaGilaiaadUgacqGHGjsUcaWGQbaabeqdcqGHris5aOWaaeWa
aeaacaWG3bWaaSbaaSqaaiaadQgacaaISaGaam4AaaqabaGccqGHsi
slcaWG3bWaaSbaaSqaaiaadMgacaaISaGaam4AaaqabaaakiaawIca
caGLPaaacqaH1oqzdaWgaaWcbaGaam4AaaqabaaakiaawUfacaGLDb
aacaaIUaaaaa@77B5@
Observons que
w
i
,
j
=
O
i
,
j
(
(
n
λ
)
−
1
)
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWG3bWaaS
baaSqaaiaadMgacaaISaGaamOAaaqabaGccaaI9aGaam4tamaaBaaa
leaacaWGPbGaaGilaiaadQgaaeqaaOWaaeWaaeaadaqadaqaaiaad6
gacqaH7oaBaiaawIcacaGLPaaadaahaaWcbeqaaiabgkHiTiaaigda
aaaakiaawIcacaGLPaaaaaa@47B2@
d’où
y
j
−
m
^
j
≤
t
−
m
^
i
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWG5bWaaS
baaSqaaiaadQgaaeqaaOGaeyOeI0IabmyBayaajaWaaSbaaSqaaiaa
dQgaaeqaaOGaeyizImQaamiDaiabgkHiTiqad2gagaqcamaaBaaale
aacaWGPbaabeaaaaa@42DE@
est (asymptotiquement, aussitôt que
c
i
,
j
>
0
)
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaadaqacaqaai
aadogadaWgaaWcbaGaamyAaiaaiYcacaWGQbaabeaakiaai6dacaaI
WaaacaGLPaaaaaa@3DEC@
équivalent à
ε
j
≤
t
−
m
i
+
d
i
,
j
.
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacqaH1oqzda
WgaaWcbaGaamOAaaqabaGccqGHKjYOcaWG0bGaeyOeI0IaamyBamaa
BaaaleaacaWGPbaabeaakiabgUcaRiaadsgadaWgaaWcbaGaamyAai
aaiYcacaWGQbaabeaakiaai6caaaa@45B9@
Comme
d
i
,
j
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWGKbWaaS
baaSqaaiaadMgacaaISaGaamOAaaqabaaaaa@3B99@
ne dépend pas de
ε
j
,
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacqaH1oqzda
WgaaWcbaGaamOAaaqabaGccaGGSaaaaa@3B6D@
il s’ensuit que
E
(
I
(
y
j
−
m
^
j
≤
t
−
m
^
i
)
)
=
E
(
I
(
ε
j
≤
t
−
m
i
+
d
i
,
j
)
)
=
E
(
E
(
I
(
ε
j
≤
t
−
m
i
+
d
i
,
j
)
|
ε
k
,
k
≠
j
)
)
=
E
(
G
(
t
−
m
i
+
d
i
,
j
|
x
j
)
)
.
(
A
.1
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrFjpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaafaqaaeWaca
aabaGaamyramaabmaabaGaamysamaabmaabaGaamyEamaaBaaaleaa
caWGQbaabeaakiabgkHiTiqad2gagaqcamaaBaaaleaacaWGQbaabe
aakiabgsMiJkaadshacqGHsislceWGTbGbaKaadaWgaaWcbaGaamyA
aaqabaaakiaawIcacaGLPaaaaiaawIcacaGLPaaaaeaacaaI9aGaam
yramaabmaabaGaamysamaabmaabaGaeqyTdu2aaSbaaSqaaiaadQga
aeqaaOGaeyizImQaamiDaiabgkHiTiaad2gadaWgaaWcbaGaamyAaa
qabaGccqGHRaWkcaWGKbWaaSbaaSqaaiaadMgacaaISaGaamOAaaqa
baaakiaawIcacaGLPaaaaiaawIcacaGLPaaaaeaaaeaacaaI9aGaam
yramaabmaabaGaamyramaabmaabaWaaqGaaeaacaWGjbWaaeWaaeaa
cqaH1oqzdaWgaaWcbaGaamOAaaqabaGccqGHKjYOcaWG0bGaeyOeI0
IaamyBamaaBaaaleaacaWGPbaabeaakiabgUcaRiaadsgadaWgaaWc
baGaamyAaiaaiYcacaWGQbaabeaaaOGaayjkaiaawMcaaiaaykW7ai
aawIa7aiaaykW7cqaH1oqzdaWgaaWcbaGaam4AaaqabaGccaaISaGa
am4AaiabgcMi5kaadQgaaiaawIcacaGLPaaaaiaawIcacaGLPaaaae
aaaeaacaaI9aGaamyramaabmaabaGaam4ramaabmaabaWaaqGaaeaa
caWG0bGaeyOeI0IaamyBamaaBaaaleaacaWGPbaabeaakiabgUcaRi
aadsgadaWgaaWcbaGaamyAaiaaiYcacaWGQbaabeaaaOGaayjcSdGa
aGjbVlaadIhadaWgaaWcbaGaamOAaaqabaaakiaawIcacaGLPaaaai
aawIcacaGLPaaacaaIUaaaaiaaywW7caaMf8UaaGzbVlaaywW7caaM
f8UaaiikaiaacgeacaGGUaGaaGymaiaacMcaaaa@9A2A@
Or, en utilisant le fait que
d
i
,
j
=
(
1
−
c
i
,
j
)
(
t
−
m
i
)
+
(
m
^
^
j
−
m
j
)
−
(
m
^
^
i
−
m
i
)
+
∑
k
∈
s
,
k
≠
j
(
w
j
,
k
−
w
i
,
k
)
ε
k
+
R
(
d
i
,
j
)
,
(
A
.2
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWGKbWaaS
baaSqaaiaadMgacaaISaGaamOAaaqabaGccaaI9aWaaeWaaeaacaaI
XaGaeyOeI0Iaam4yamaaBaaaleaacaWGPbGaaGilaiaadQgaaeqaaa
GccaGLOaGaayzkaaWaaeWaaeaacaWG0bGaeyOeI0IaamyBamaaBaaa
leaacaWGPbaabeaaaOGaayjkaiaawMcaaiabgUcaRmaabmaabaGabm
yBayaajyaajaWaaSbaaSqaaiaadQgaaeqaaOGaeyOeI0IaamyBamaa
BaaaleaacaWGQbaabeaaaOGaayjkaiaawMcaaiabgkHiTmaabmaaba
GabmyBayaajyaajaWaaSbaaSqaaiaadMgaaeqaaOGaeyOeI0IaamyB
amaaBaaaleaacaWGPbaabeaaaOGaayjkaiaawMcaaiabgUcaRmaaqa
fabeWcbaGaam4AaiabgIGiolaadohacaaISaGaam4AaiabgcMi5kaa
dQgaaeqaniabggHiLdGcdaqadaqaaiaadEhadaWgaaWcbaGaamOAai
aaiYcacaWGRbaabeaakiabgkHiTiaadEhadaWgaaWcbaGaamyAaiaa
iYcacaWGRbaabeaaaOGaayjkaiaawMcaaiabew7aLnaaBaaaleaaca
WGRbaabeaakiabgUcaRiaadkfadaqadaqaaiaadsgadaWgaaWcbaGa
amyAaiaaiYcacaWGQbaabeaaaOGaayjkaiaawMcaaiaaiYcacaaMf8
UaaGzbVlaaywW7caaMf8UaaiikaiaacgeacaGGUaGaaGOmaiaacMca
aaa@8139@
où
E
1
/
4
(
|
R
(
d
i
,
j
)
|
4
)
=
O
i
,
j
(
λ
n
−
1
+
(
n
λ
)
−
3
/
2
)
,
(
A
.3
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWGfbWaaW
baaSqabeaadaWcgaqaaiaaigdaaeaacaaI0aaaaaaakmaabmaabaGa
aGPaVpaaemaabaGaaGPaVlaadkfadaqadaqaaiaadsgadaWgaaWcba
GaamyAaiaaiYcacaWGQbaabeaaaOGaayjkaiaawMcaaiaaykW7aiaa
wEa7caGLiWoadaahaaWcbeqaaiaaykW7caaI0aaaaaGccaGLOaGaay
zkaaGaaGypaiaad+eadaWgaaWcbaGaamyAaiaaiYcacaWGQbaabeaa
kmaabmaabaGaeq4UdWMaamOBamaaCaaaleqabaGaeyOeI0IaaGymaa
aakiabgUcaRmaabmaabaGaamOBaiabeU7aSbGaayjkaiaawMcaamaa
CaaaleqabaGaeyOeI0YaaSGbaeaacaaIZaaabaGaaGOmaaaaaaaaki
aawIcacaGLPaaacaaISaGaaGzbVlaaywW7caaMf8UaaGzbVlaaywW7
caGGOaGaaiyqaiaac6cacaaIZaGaaiykaaaa@6A9F@
on voit en examinant (A.1) que
E
(
I
(
y
j
−
m
^
j
≤
t
−
m
^
i
)
)
=
E
(
G
(
t
−
m
i
+
d
i
,
j
)
|
x
j
)
=
G
(
t
−
m
i
|
x
j
)
+
G
(
1,0
)
(
t
−
m
i
|
x
j
)
E
(
d
i
,
j
)
+
1
2
G
(
2,0
)
(
t
−
m
i
|
x
j
)
E
(
d
i
,
j
2
)
+
o
i
,
j
(
λ
4
+
(
n
λ
)
−
1
)
.
(
A
.4
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaafaqaaeWaca
aabaGaamyramaabmaabaGaamysamaabmaabaGaamyEamaaBaaaleaa
caWGQbaabeaakiabgkHiTiqad2gagaqcamaaBaaaleaacaWGQbaabe
aakiabgsMiJkaadshacqGHsislceWGTbGbaKaadaWgaaWcbaGaamyA
aaqabaaakiaawIcacaGLPaaaaiaawIcacaGLPaaaaeaacaaI9aGaam
yramaabmaabaWaaqGaaeaacaWGhbWaaeWaaeaacaWG0bGaeyOeI0Ia
amyBamaaBaaaleaacaWGPbaabeaakiabgUcaRiaadsgadaWgaaWcba
GaamyAaiaaiYcacaWGQbaabeaaaOGaayjkaiaawMcaaiaaykW7aiaa
wIa7aiaaysW7caWG4bWaaSbaaSqaaiaadQgaaeqaaaGccaGLOaGaay
zkaaaabaaabaGaaGypaiaadEeadaqadaqaamaaeiaabaGaamiDaiab
gkHiTiaad2gadaWgaaWcbaGaamyAaaqabaaakiaawIa7aiaaysW7ca
WG4bWaaSbaaSqaaiaadQgaaeqaaaGccaGLOaGaayzkaaGaey4kaSIa
am4ramaaCaaaleqabaWaaeWaaeaacaaIXaGaaGilaiaaicdaaiaawI
cacaGLPaaaaaGcdaqadaqaamaaeiaabaGaamiDaiabgkHiTiaad2ga
daWgaaWcbaGaamyAaaqabaaakiaawIa7aiaaysW7caWG4bWaaSbaaS
qaaiaadQgaaeqaaaGccaGLOaGaayzkaaGaamyramaabmaabaGaamiz
amaaBaaaleaacaWGPbGaaGilaiaadQgaaeqaaaGccaGLOaGaayzkaa
aabaaabaGaaGjbVlaaysW7cqGHRaWkdaWcaaqaaiaaigdaaeaacaaI
YaaaaiaadEeadaahaaWcbeqaamaabmaabaGaaGOmaiaaiYcacaaIWa
aacaGLOaGaayzkaaaaaOWaaeWaaeaadaabcaqaaiaadshacqGHsisl
caWGTbWaaSbaaSqaaiaadMgaaeqaaaGccaGLiWoacaaMe8UaamiEam
aaBaaaleaacaWGQbaabeaaaOGaayjkaiaawMcaaiaadweadaqadaqa
aiaadsgadaqhaaWcbaGaamyAaiaaiYcacaWGQbaabaGaaGOmaaaaaO
GaayjkaiaawMcaaiabgUcaRiaad+gadaWgaaWcbaGaamyAaiaaiYca
caWGQbaabeaakmaabmaabaGaeq4UdW2aaWbaaSqabeaacaaI0aaaaO
Gaey4kaSYaaeWaaeaacaWGUbGaeq4UdWgacaGLOaGaayzkaaWaaWba
aSqabeaacqGHsislcaaIXaaaaaGccaGLOaGaayzkaaGaaGOlaaaaca
aMf8UaaGzbVlaaywW7caaMf8UaaiikaiaacgeacaGGUaGaaGinaiaa
cMcaaaa@B53F@
Donc,
E
(
F
^
*
(
t
)
−
F
N
(
t
)
)
=
E
(
1
N
∑
i
∉
s
∑
j
∈
s
w
i
,
j
(
I
(
y
j
−
m
^
j
≤
t
−
m
^
i
)
−
I
(
y
i
≤
t
)
)
)
=
1
N
∑
i
∉
s
∑
j
∈
s
w
i
,
j
[
G
(
t
−
m
i
|
x
j
)
−
G
(
t
−
m
i
|
x
i
)
]
+
1
N
∑
i
∉
s
∑
j
∈
s
w
i
,
j
G
(
1
,
0
)
(
t
−
m
i
|
x
j
)
E
(
d
i
,
j
)
+
1
2
N
∑
i
∉
s
∑
j
∈
s
w
i
,
j
G
(
2
,
0
)
(
t
−
m
i
|
x
j
)
E
(
d
i
,
j
2
)
+
o
(
λ
4
+
(
n
λ
)
−
1
)
:=
C
1
+
C
2
+
C
3
+
o
(
λ
4
+
(
n
λ
)
−
1
)
.
(
A
.5
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrFfpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaafaqaaeqbca
aaaeaacaWGfbWaaeWaaeaaceWGgbGbaKaadaahaaWcbeqaaiaaiQca
aaGccaaMb8+aaeWaaeaacaWG0baacaGLOaGaayzkaaGaeyOeI0Iaam
OramaaBaaaleaacaWGobaabeaakmaabmaabaGaamiDaaGaayjkaiaa
wMcaaaGaayjkaiaawMcaaaqaaiaai2dacaWGfbWaaeWaaeaadaWcaa
qaaiaaigdaaeaacaWGobaaamaaqafabeWcbaGaamyAaiabgMGiplaa
dohaaeqaniabggHiLdGcdaaeqbqaaiaadEhadaWgaaWcbaGaamyAai
aaiYcacaWGQbaabeaaaeaacaWGQbGaeyicI4Saam4Caaqab0Gaeyye
IuoakmaabmaabaGaamysamaabmaabaGaamyEamaaBaaaleaacaWGQb
aabeaakiabgkHiTiqad2gagaqcamaaBaaaleaacaWGQbaabeaakiab
gsMiJkaadshacqGHsislceWGTbGbaKaadaWgaaWcbaGaamyAaaqaba
aakiaawIcacaGLPaaacqGHsislcaWGjbWaaeWaaeaacaWG5bWaaSba
aSqaaiaadMgaaeqaaOGaeyizImQaamiDaaGaayjkaiaawMcaaaGaay
jkaiaawMcaaaGaayjkaiaawMcaaaqaaaqaaiaai2dadaWcaaqaaiaa
igdaaeaacaWGobaaamaaqafabeWcbaGaamyAaiabgMGiplaadohaae
qaniabggHiLdGcdaaeqbqaaiaadEhadaWgaaWcbaGaamyAaiaaiYca
caWGQbaabeaaaeaacaWGQbGaeyicI4Saam4Caaqab0GaeyyeIuoakm
aadmaabaGaam4ramaabmaabaWaaqGaaeaacaWG0bGaeyOeI0IaamyB
amaaBaaaleaacaWGPbaabeaaaOGaayjcSdGaaGjbVlaadIhadaWgaa
WcbaGaamOAaaqabaaakiaawIcacaGLPaaacqGHsislcaWGhbWaaeWa
aeaadaabcaqaaiaadshacqGHsislcaWGTbWaaSbaaSqaaiaadMgaae
qaaaGccaGLiWoacaaMe8UaamiEamaaBaaaleaacaWGPbaabeaaaOGa
ayjkaiaawMcaaaGaay5waiaaw2faaaqaaaqaaiaaysW7caaMe8Uaey
4kaSYaaSaaaeaacaaIXaaabaGaamOtaaaadaaeqbqabSqaaiaadMga
cqGHjiYZcaWGZbaabeqdcqGHris5aOWaaabuaeaacaWG3bWaaSbaaS
qaaiaadMgacaaISaGaamOAaaqabaGccaWGhbWaaWbaaSqabeaadaqa
daqaaiaaigdacaGGSaGaaGimaaGaayjkaiaawMcaaaaaaeaacaWGQb
GaeyicI4Saam4Caaqab0GaeyyeIuoakmaabmaabaWaaqGaaeaacaWG
0bGaeyOeI0IaamyBamaaBaaaleaacaWGPbaabeaaaOGaayjcSdGaaG
jbVlaadIhadaWgaaWcbaGaamOAaaqabaaakiaawIcacaGLPaaacaWG
fbWaaeWaaeaacaWGKbWaaSbaaSqaaiaadMgacaaISaGaamOAaaqaba
aakiaawIcacaGLPaaaaeaaaeaacaaMe8UaaGjbVlabgUcaRmaalaaa
baGaaGymaaqaaiaaikdacaWGobaaamaaqafabeWcbaGaamyAaiabgM
GiplaadohaaeqaniabggHiLdGcdaaeqbqaaiaadEhadaWgaaWcbaGa
amyAaiaaiYcacaWGQbaabeaakiaadEeadaahaaWcbeqaamaabmaaba
GaaGOmaiaacYcacaaIWaaacaGLOaGaayzkaaaaaaqaaiaadQgacqGH
iiIZcaWGZbaabeqdcqGHris5aOWaaeWaaeaadaabcaqaaiaadshacq
GHsislcaWGTbWaaSbaaSqaaiaadMgaaeqaaaGccaGLiWoacaaMe8Ua
amiEamaaBaaaleaacaWGQbaabeaaaOGaayjkaiaawMcaaiaadweada
qadaqaaiaadsgadaqhaaWcbaGaamyAaiaaiYcacaWGQbaabaGaaGOm
aaaaaOGaayjkaiaawMcaaiabgUcaRiaad+gadaqadaqaaiabeU7aSn
aaCaaaleqabaGaaGinaaaakiabgUcaRmaabmaabaGaamOBaiabeU7a
SbGaayjkaiaawMcaamaaCaaaleqabaGaeyOeI0IaaGymaaaaaOGaay
jkaiaawMcaaaqaaaqaaiaaiQdacaaI9aGaam4qamaaBaaaleaacaaI
XaaabeaakiabgUcaRiaadoeadaWgaaWcbaGaaGOmaaqabaGccqGHRa
WkcaWGdbWaaSbaaSqaaiaaiodaaeqaaOGaey4kaSIaam4Bamaabmaa
baGaeq4UdW2aaWbaaSqabeaacaaI0aaaaOGaey4kaSYaaeWaaeaaca
WGUbGaeq4UdWgacaGLOaGaayzkaaWaaWbaaSqabeaacqGHsislcaaI
XaaaaaGccaGLOaGaayzkaaGaaGOlaaaacaaMf8UaaGzbVlaaywW7ca
GGOaGaaiyqaiaac6cacaaI1aGaaiykaaaa@1C16@
Considérons d’abord
C
1
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWGdbWaaS
baaSqaaiaaigdaaeqaaaaa@39A0@
et notons que
C
1
:=
1
N
∑
i
∉
s
∑
j
∈
s
w
i
,
j
[
G
(
t
−
m
i
|
x
j
)
−
G
(
t
−
m
i
|
x
i
)
]
=
1
2
N
∑
i
∉
s
G
(
0
,
2
)
(
t
−
m
i
|
x
i
)
∑
j
∈
s
w
i
,
j
(
x
j
−
x
i
)
2
+
o
(
λ
2
)
=
λ
2
N
−
n
N
μ
2
μ
0
∫
a
b
G
(
0
,
2
)
(
t
−
m
(
x
)
|
x
)
h
s
¯
(
x
)
d
x
+
o
(
λ
2
)
.
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaafaqaaeWaca
aabaGaam4qamaaBaaaleaacaaIXaaabeaaaOqaaiaaiQdacaaI9aWa
aSaaaeaacaaIXaaabaGaamOtaaaadaaeqbqabSqaaiaadMgacqGHji
YZcaWGZbaabeqdcqGHris5aOWaaabuaeaacaWG3bWaaSbaaSqaaiaa
dMgacaaISaGaamOAaaqabaaabaGaamOAaiabgIGiolaadohaaeqani
abggHiLdGcdaWadaqaaiaadEeadaqadaqaamaaeiaabaGaamiDaiab
gkHiTiaad2gadaWgaaWcbaGaamyAaaqabaaakiaawIa7aiaaysW7ca
WG4bWaaSbaaSqaaiaadQgaaeqaaaGccaGLOaGaayzkaaGaeyOeI0Ia
am4ramaabmaabaWaaqGaaeaacaWG0bGaeyOeI0IaamyBamaaBaaale
aacaWGPbaabeaaaOGaayjcSdGaaGjbVlaadIhadaWgaaWcbaGaamyA
aaqabaaakiaawIcacaGLPaaaaiaawUfacaGLDbaaaeaaaeaacaaI9a
WaaSaaaeaacaaIXaaabaGaaGOmaiaad6eaaaWaaabuaeaacaWGhbWa
aWbaaSqabeaadaqadaqaaiaaicdacaGGSaGaaGOmaaGaayjkaiaawM
caaaaaaeaacaWGPbGaeyycI8Saam4Caaqab0GaeyyeIuoakmaabmaa
baWaaqGaaeaacaWG0bGaeyOeI0IaamyBamaaBaaaleaacaWGPbaabe
aaaOGaayjcSdGaaGjbVlaadIhadaWgaaWcbaGaamyAaaqabaaakiaa
wIcacaGLPaaadaaeqbqaaiaadEhadaWgaaWcbaGaamyAaiaaiYcaca
WGQbaabeaaaeaacaWGQbGaeyicI4Saam4Caaqab0GaeyyeIuoakmaa
bmaabaGaamiEamaaBaaaleaacaWGQbaabeaakiabgkHiTiaadIhada
WgaaWcbaGaamyAaaqabaaakiaawIcacaGLPaaadaahaaWcbeqaaiaa
ikdaaaGccqGHRaWkcaWGVbWaaeWaaeaacqaH7oaBdaahaaWcbeqaai
aaikdaaaaakiaawIcacaGLPaaaaeaaaeaacaaI9aGaeq4UdW2aaWba
aSqabeaacaaIYaaaaOWaaSaaaeaacaWGobGaeyOeI0IaamOBaaqaai
aad6eaaaWaaSaaaeaacqaH8oqBdaWgaaWcbaGaaGOmaaqabaaakeaa
cqaH8oqBdaWgaaWcbaGaaGimaaqabaaaaOWaa8qmaeaacaWGhbWaaW
baaSqabeaadaqadaqaaiaaicdacaGGSaGaaGOmaaGaayjkaiaawMca
aaaaaeaacaWGHbaabaGaamOyaaqdcqGHRiI8aOWaaeWaaeaadaabca
qaaiaadshacqGHsislcaWGTbWaaeWaaeaacaWG4baacaGLOaGaayzk
aaGaaGPaVdGaayjcSdGaaGjbVlaadIhaaiaawIcacaGLPaaacaWGOb
WaaSbaaSqaaiaaykW7ceWGZbGbaebaaeqaaOWaaeWaaeaacaWG4baa
caGLOaGaayzkaaGaamizaiaadIhacqGHRaWkcaWGVbWaaeWaaeaacq
aH7oaBdaahaaWcbeqaaiaaikdaaaaakiaawIcacaGLPaaacaaIUaaa
aaaa@C563@
Considérons ensuite
C
2
.
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWGdbWaaS
baaSqaaiaaikdaaeqaaOGaaiOlaaaa@3A5D@
(A.2) et (A.3) impliquent que
E
(
d
i
,
j
)
=
(
1
−
c
i
,
j
)
(
t
−
m
i
)
+
(
m
^
^
j
−
m
j
)
−
(
m
^
^
i
−
m
i
)
+
O
i
,
j
(
λ
n
−
1
+
(
n
λ
)
−
3
/
2
)
=
(
w
j
,
j
−
w
i
,
j
)
(
t
−
m
i
)
+
m
j
′′
∑
k
∈
s
w
j
,
k
(
x
k
−
x
j
)
2
−
m
i
′′
∑
k
∈
s
w
i
,
k
(
x
k
−
x
i
)
2
+
o
i
,
j
(
λ
2
)
+
O
i
,
j
(
λ
n
−
1
+
(
n
λ
)
−
3
/
2
)
=
(
w
j
,
j
−
w
i
,
j
)
(
t
−
m
i
)
+
(
m
j
′′
−
m
i
′′
)
∑
k
∈
s
w
j
,
k
(
x
k
−
x
j
)
2
+
m
i
′′
(
∑
k
∈
s
w
j
,
k
(
x
k
−
x
j
)
2
−
∑
k
∈
s
w
i
,
k
(
x
k
−
x
i
)
2
)
+
o
i
,
j
(
λ
2
)
+
O
i
,
j
(
λ
n
−
1
+
(
n
λ
)
−
3
/
2
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrFfpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaafaqaaeGbca
aaaeaacaWGfbWaaeWaaeaacaWGKbWaaSbaaSqaaiaadMgacaaISaGa
amOAaaqabaaakiaawIcacaGLPaaaaeaacaaI9aWaaeWaaeaacaaIXa
GaeyOeI0Iaam4yamaaBaaaleaacaWGPbGaaGilaiaadQgaaeqaaaGc
caGLOaGaayzkaaWaaeWaaeaacaWG0bGaeyOeI0IaamyBamaaBaaale
aacaWGPbaabeaaaOGaayjkaiaawMcaaiabgUcaRmaabmaabaGabmyB
ayaajyaajaWaaSbaaSqaaiaadQgaaeqaaOGaeyOeI0IaamyBamaaBa
aaleaacaWGQbaabeaaaOGaayjkaiaawMcaaiabgkHiTmaabmaabaGa
bmyBayaajyaajaWaaSbaaSqaaiaadMgaaeqaaOGaeyOeI0IaamyBam
aaBaaaleaacaWGPbaabeaaaOGaayjkaiaawMcaaiabgUcaRiaad+ea
daWgaaWcbaGaamyAaiaaiYcacaWGQbaabeaakmaabmaabaGaeq4UdW
MaamOBamaaCaaaleqabaGaeyOeI0IaaGymaaaakiabgUcaRmaabmaa
baGaamOBaiabeU7aSbGaayjkaiaawMcaamaaCaaaleqabaGaeyOeI0
YaaSGbaeaacaaIZaaabaGaaGOmaaaaaaaakiaawIcacaGLPaaaaeaa
aeaacaaI9aWaaeWaaeaacaWG3bWaaSbaaSqaaiaadQgacaaISaGaam
OAaaqabaGccqGHsislcaWG3bWaaSbaaSqaaiaadMgacaaISaGaamOA
aaqabaaakiaawIcacaGLPaaadaqadaqaaiaadshacqGHsislcaWGTb
WaaSbaaSqaaiaadMgaaeqaaaGccaGLOaGaayzkaaGaey4kaSIabmyB
ayaagaWaaSbaaSqaaiaadQgaaeqaaOGaaGjbVpaaqafabaGaam4Dam
aaBaaaleaacaWGQbGaaGilaiaadUgaaeqaaOWaaeWaaeaacaWG4bWa
aSbaaSqaaiaadUgaaeqaaOGaeyOeI0IaamiEamaaBaaaleaacaWGQb
aabeaaaOGaayjkaiaawMcaamaaCaaaleqabaGaaGOmaaaaaeaacaWG
RbGaeyicI4Saam4Caaqab0GaeyyeIuoakiabgkHiTiqad2gagaGbam
aaBaaaleaacaWGPbaabeaakiaaysW7daaeqbqaaiaadEhadaWgaaWc
baGaamyAaiaaiYcacaWGRbaabeaakmaabmaabaGaamiEamaaBaaale
aacaWGRbaabeaakiabgkHiTiaadIhadaWgaaWcbaGaamyAaaqabaaa
kiaawIcacaGLPaaadaahaaWcbeqaaiaaikdaaaaabaGaam4AaiabgI
GiolaadohaaeqaniabggHiLdaakeaaaeaacaaMe8UaaGjbVlabgUca
Riaad+gadaWgaaWcbaGaamyAaiaaiYcacaWGQbaabeaakmaabmaaba
Gaeq4UdW2aaWbaaSqabeaacaaIYaaaaaGccaGLOaGaayzkaaGaey4k
aSIaam4tamaaBaaaleaacaWGPbGaaGilaiaadQgaaeqaaOWaaeWaae
aacqaH7oaBcaWGUbWaaWbaaSqabeaacqGHsislcaaIXaaaaOGaey4k
aSYaaeWaaeaacaWGUbGaeq4UdWgacaGLOaGaayzkaaWaaWbaaSqabe
aacqGHsisldaWcgaqaaiaaiodaaeaacaaIYaaaaaaaaOGaayjkaiaa
wMcaaaqaaaqaaiaai2dadaqadaqaaiaadEhadaWgaaWcbaGaamOAai
aaiYcacaWGQbaabeaakiabgkHiTiaadEhadaWgaaWcbaGaamyAaiaa
iYcacaWGQbaabeaaaOGaayjkaiaawMcaamaabmaabaGaamiDaiabgk
HiTiaad2gadaWgaaWcbaGaamyAaaqabaaakiaawIcacaGLPaaacqGH
RaWkdaqadaqaaiqad2gagaGbamaaBaaaleaacaWGQbaabeaakiabgk
HiTiqad2gagaGbamaaBaaaleaacaWGPbaabeaaaOGaayjkaiaawMca
amaaqafabaGaam4DamaaBaaaleaacaWGQbGaaGilaiaadUgaaeqaaO
WaaeWaaeaacaWG4bWaaSbaaSqaaiaadUgaaeqaaOGaeyOeI0IaamiE
amaaBaaaleaacaWGQbaabeaaaOGaayjkaiaawMcaamaaCaaaleqaba
GaaGOmaaaaaeaacaWGRbGaeyicI4Saam4Caaqab0GaeyyeIuoaaOqa
aaqaaiaaysW7caaMe8Uaey4kaSIabmyBayaagaWaaSbaaSqaaiaadM
gaaeqaaOGaaGjbVpaabmaabaWaaabuaeaacaWG3bWaaSbaaSqaaiaa
dQgacaaISaGaam4AaaqabaGcdaqadaqaaiaadIhadaWgaaWcbaGaam
4AaaqabaGccqGHsislcaWG4bWaaSbaaSqaaiaadQgaaeqaaaGccaGL
OaGaayzkaaWaaWbaaSqabeaacaaIYaaaaaqaaiaadUgacqGHiiIZca
WGZbaabeqdcqGHris5aOGaeyOeI0YaaabuaeaacaWG3bWaaSbaaSqa
aiaadMgacaaISaGaam4AaaqabaGcdaqadaqaaiaadIhadaWgaaWcba
Gaam4AaaqabaGccqGHsislcaWG4bWaaSbaaSqaaiaadMgaaeqaaaGc
caGLOaGaayzkaaWaaWbaaSqabeaacaaIYaaaaaqaaiaadUgacqGHii
IZcaWGZbaabeqdcqGHris5aaGccaGLOaGaayzkaaaabaaabaGaaGjb
VlaaysW7cqGHRaWkcaWGVbWaaSbaaSqaaiaadMgacaaISaGaamOAaa
qabaGcdaqadaqaaiabeU7aSnaaCaaaleqabaGaaGOmaaaaaOGaayjk
aiaawMcaaiabgUcaRiaad+eadaWgaaWcbaGaamyAaiaaiYcacaWGQb
aabeaakmaabmaabaGaeq4UdWMaamOBamaaCaaaleqabaGaeyOeI0Ia
aGymaaaakiabgUcaRmaabmaabaGaamOBaiabeU7aSbGaayjkaiaawM
caamaaCaaaleqabaGaeyOeI0YaaSGbaeaacaaIZaaabaGaaGOmaaaa
aaaakiaawIcacaGLPaaaaaaaaa@39BD@
de sorte que
C
2
=
C
2,
a
+
C
2,
b
+
C
2,
c
+
o
(
λ
2
)
+
O
(
λ
n
−
1
+
(
n
λ
)
−
3
/
2
)
,
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWGdbWaaS
baaSqaaiaaikdaaeqaaOGaaGypaiaadoeadaWgaaWcbaGaaGOmaiaa
iYcacaWGHbaabeaakiabgUcaRiaadoeadaWgaaWcbaGaaGOmaiaaiY
cacaWGIbaabeaakiabgUcaRiaadoeadaWgaaWcbaGaaGOmaiaaiYca
caWGJbaabeaakiabgUcaRiaad+gadaqadaqaaiabeU7aSnaaCaaale
qabaGaaGOmaaaaaOGaayjkaiaawMcaaiabgUcaRiaad+eadaqadaqa
aiabeU7aSjaad6gadaahaaWcbeqaaiabgkHiTiaaigdaaaGccqGHRa
Wkdaqadaqaaiaad6gacqaH7oaBaiaawIcacaGLPaaadaahaaWcbeqa
aiabgkHiTmaalyaabaGaaG4maaqaaiaaikdaaaaaaaGccaGLOaGaay
zkaaGaaGilaaaa@5C80@
où
C
2,
a
:=
1
N
∑
i
∉
s
∑
j
∈
s
w
i
,
j
G
(
1
,
0
)
(
t
−
m
i
|
x
j
)
(
w
j
,
j
−
w
i
,
j
)
(
t
−
m
i
)
=
1
N
∑
i
∉
s
G
(
1
,
0
)
(
t
−
m
i
|
x
i
)
(
t
−
m
i
)
∑
j
∈
s
w
i
,
j
(
w
j
,
j
−
w
i
,
j
)
+
O
(
n
−
1
)
=
1
n
λ
N
−
n
N
K
(
0
)
−
κ
μ
0
∫
a
b
G
(
1
,
0
)
(
t
−
m
(
x
)
|
x
)
(
t
−
m
(
x
)
)
[
h
s
¯
(
x
)
/
h
s
(
x
)
]
d
x
+
O
(
(
n
λ
)
−
1
λ
−
1
α
+
n
−
1
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaafaqaaeabca
aaaeaacaWGdbWaaSbaaSqaaiaaikdacaaISaGaamyyaaqabaaakeaa
caaI6aGaaGypamaalaaabaGaaGymaaqaaiaad6eaaaWaaabuaeqale
aacaWGPbGaeyycI8Saam4Caaqab0GaeyyeIuoakmaaqafabaGaam4D
amaaBaaaleaacaWGPbGaaGilaiaadQgaaeqaaOGaam4ramaaCaaale
qabaWaaeWaaeaacaaIXaGaaiilaiaaicdaaiaawIcacaGLPaaaaaaa
baGaamOAaiabgIGiolaadohaaeqaniabggHiLdGcdaqadaqaamaaei
aabaGaamiDaiabgkHiTiaad2gadaWgaaWcbaGaamyAaaqabaaakiaa
wIa7aiaaysW7caWG4bWaaSbaaSqaaiaadQgaaeqaaaGccaGLOaGaay
zkaaWaaeWaaeaacaWG3bWaaSbaaSqaaiaadQgacaaISaGaamOAaaqa
baGccqGHsislcaWG3bWaaSbaaSqaaiaadMgacaaISaGaamOAaaqaba
aakiaawIcacaGLPaaadaqadaqaaiaadshacqGHsislcaWGTbWaaSba
aSqaaiaadMgaaeqaaaGccaGLOaGaayzkaaaabaaabaGaaGypamaala
aabaGaaGymaaqaaiaad6eaaaWaaabuaeaacaWGhbWaaWbaaSqabeaa
daqadaqaaiaaigdacaGGSaGaaGimaaGaayjkaiaawMcaaaaaaeaaca
WGPbGaeyycI8Saam4Caaqab0GaeyyeIuoakmaabmaabaWaaqGaaeaa
caWG0bGaeyOeI0IaamyBamaaBaaaleaacaWGPbaabeaaaOGaayjcSd
GaaGjbVlaadIhadaWgaaWcbaGaamyAaaqabaaakiaawIcacaGLPaaa
daqadaqaaiaadshacqGHsislcaWGTbWaaSbaaSqaaiaadMgaaeqaaa
GccaGLOaGaayzkaaWaaabuaeaacaWG3bWaaSbaaSqaaiaadMgacaaI
SaGaamOAaaqabaaabaGaamOAaiabgIGiolaadohaaeqaniabggHiLd
GcdaqadaqaaiaadEhadaWgaaWcbaGaamOAaiaaiYcacaWGQbaabeaa
kiabgkHiTiaadEhadaWgaaWcbaGaamyAaiaaiYcacaWGQbaabeaaaO
GaayjkaiaawMcaaiabgUcaRiaad+eadaqadaqaaiaad6gadaahaaWc
beqaaiabgkHiTiaaigdaaaaakiaawIcacaGLPaaaaeaaaeaacaaI9a
WaaSaaaeaacaaIXaaabaGaamOBaiabeU7aSbaadaWcaaqaaiaad6ea
cqGHsislcaWGUbaabaGaamOtaaaadaWcaaqaaiaadUeadaqadaqaai
aaicdaaiaawIcacaGLPaaacqGHsislcqaH6oWAaeaacqaH8oqBdaWg
aaWcbaGaaGimaaqabaaaaOWaa8qmaeqaleaacaWGHbaabaGaamOyaa
qdcqGHRiI8aOGaam4ramaaCaaaleqabaWaaeWaaeaacaaIXaGaaiil
aiaaicdaaiaawIcacaGLPaaaaaGcdaqadaqaamaaeiaabaGaamiDai
abgkHiTiaad2gadaqadaqaaiaadIhaaiaawIcacaGLPaaacaaMc8oa
caGLiWoacaaMe8UaamiEaaGaayjkaiaawMcaamaabmaabaGaamiDai
abgkHiTiaad2gadaqadaqaaiaadIhaaiaawIcacaGLPaaaaiaawIca
caGLPaaadaWadaqaamaalyaabaGaamiAamaaBaaaleaacaaMc8Uabm
4CayaaraaabeaakmaabmaabaGaamiEaaGaayjkaiaawMcaaaqaaiaa
dIgadaWgaaWcbaGaam4CaaqabaGcdaqadaqaaiaadIhaaiaawIcaca
GLPaaaaaaacaGLBbGaayzxaaGaamizaiaadIhaaeaaaeaacaaMe8Ua
aGjbVlabgUcaRiaad+eadaqadaqaamaabmaabaGaamOBaiabeU7aSb
GaayjkaiaawMcaamaaCaaaleqabaGaeyOeI0IaaGymaaaakiabeU7a
SnaaCaaaleqabaGaeyOeI0IaaGymaaaakiabeg7aHjabgUcaRiaad6
gadaahaaWcbeqaaiabgkHiTiaaigdaaaaakiaawIcacaGLPaaaaaaa
aa@F32C@
avec
κ
:=
∫
−
1
1
K
2
(
u
)
d
u
,
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacqaH6oWAca
aI6aGaaGypamaapedabaGaam4samaaCaaaleqabaGaaGOmaaaaaeaa
cqGHsislcaaIXaaabaGaaGymaaqdcqGHRiI8aOWaaeWaaeaacaWG1b
aacaGLOaGaayzkaaGaamizaiaadwhacaGGSaaaaa@4688@
C
2,
b
:=
1
N
∑
i
∉
s
∑
j
∈
s
w
i
,
j
G
(
1
,
0
)
(
t
−
m
i
|
x
j
)
(
m
j
′′
−
m
i
′′
)
∑
k
∈
s
w
j
,
k
(
x
k
−
x
j
)
2
=
o
(
λ
2
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaafaqaaeGaca
aabaGaam4qamaaBaaaleaacaaIYaGaaGilaiaadkgaaeqaaaGcbaGa
aGOoaiaai2dadaWcaaqaaiaaigdaaeaacaWGobaaamaaqafabeWcba
GaamyAaiabgMGiplaadohaaeqaniabggHiLdGcdaaeqbqaaiaadEha
daWgaaWcbaGaamyAaiaaiYcacaWGQbaabeaakiaadEeadaahaaWcbe
qaamaabmaabaGaaGymaiaacYcacaaIWaaacaGLOaGaayzkaaaaaaqa
aiaadQgacqGHiiIZcaWGZbaabeqdcqGHris5aOWaaeWaaeaadaabca
qaaiaadshacqGHsislcaWGTbWaaSbaaSqaaiaadMgaaeqaaaGccaGL
iWoacaaMe8UaamiEamaaBaaaleaacaWGQbaabeaaaOGaayjkaiaawM
caamaabmaabaGabmyBayaagaWaaSbaaSqaaiaadQgaaeqaaOGaeyOe
I0IabmyBayaagaWaaSbaaSqaaiaadMgaaeqaaaGccaGLOaGaayzkaa
WaaabuaeaacaWG3bWaaSbaaSqaaiaadQgacaaISaGaam4AaaqabaGc
daqadaqaaiaadIhadaWgaaWcbaGaam4AaaqabaGccqGHsislcaWG4b
WaaSbaaSqaaiaadQgaaeqaaaGccaGLOaGaayzkaaWaaWbaaSqabeaa
caaIYaaaaaqaaiaadUgacqGHiiIZcaWGZbaabeqdcqGHris5aaGcba
aabaGaaGypaiaad+gadaqadaqaaiabeU7aSnaaCaaaleqabaGaaGOm
aaaaaOGaayjkaiaawMcaaaaaaaa@7A7D@
et
C
2,
c
:=
1
N
∑
i
∉
s
∑
j
∈
s
w
i
,
j
G
(
1
,
0
)
(
t
−
m
i
|
x
j
)
m
i
′′
(
∑
k
∈
s
w
j
,
k
(
x
k
−
x
j
)
2
−
∑
k
∈
s
w
i
,
k
(
x
k
−
x
i
)
2
)
=
1
N
∑
i
∉
s
G
(
1
,
0
)
(
t
−
m
i
|
x
i
)
m
i
′′
(
∑
j
∈
s
w
i
,
j
∑
k
∈
s
w
j
,
k
(
x
k
−
x
j
)
2
−
∑
k
∈
s
w
i
,
k
(
x
k
−
x
i
)
2
)
+
o
(
λ
2
)
=
o
(
λ
2
)
.
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaafaqaaeWaca
aabaGaam4qamaaBaaaleaacaaIYaGaaGilaiaadogaaeqaaaGcbaGa
aGOoaiaai2dadaWcaaqaaiaaigdaaeaacaWGobaaamaaqafabeWcba
GaamyAaiabgMGiplaadohaaeqaniabggHiLdGcdaaeqbqaaiaadEha
daWgaaWcbaGaamyAaiaaiYcacaWGQbaabeaakiaadEeadaahaaWcbe
qaamaabmaabaGaaGymaiaacYcacaaIWaaacaGLOaGaayzkaaaaaaqa
aiaadQgacqGHiiIZcaWGZbaabeqdcqGHris5aOWaaeWaaeaadaabca
qaaiaadshacqGHsislcaWGTbWaaSbaaSqaaiaadMgaaeqaaaGccaGL
iWoacaaMe8UaamiEamaaBaaaleaacaWGQbaabeaaaOGaayjkaiaawM
caaiqad2gagaGbamaaBaaaleaacaWGPbaabeaakiaaysW7daqadaqa
amaaqafabaGaam4DamaaBaaaleaacaWGQbGaaGilaiaadUgaaeqaaO
WaaeWaaeaacaWG4bWaaSbaaSqaaiaadUgaaeqaaOGaeyOeI0IaamiE
amaaBaaaleaacaWGQbaabeaaaOGaayjkaiaawMcaamaaCaaaleqaba
GaaGOmaaaaaeaacaWGRbGaeyicI4Saam4Caaqab0GaeyyeIuoakiab
gkHiTmaaqafabaGaam4DamaaBaaaleaacaWGPbGaaGilaiaadUgaae
qaaOWaaeWaaeaacaWG4bWaaSbaaSqaaiaadUgaaeqaaOGaeyOeI0Ia
amiEamaaBaaaleaacaWGPbaabeaaaOGaayjkaiaawMcaamaaCaaale
qabaGaaGOmaaaaaeaacaWGRbGaeyicI4Saam4Caaqab0GaeyyeIuoa
aOGaayjkaiaawMcaaaqaaaqaaiaai2dadaWcaaqaaiaaigdaaeaaca
WGobaaamaaqafabaGaam4ramaaCaaaleqabaWaaeWaaeaacaaIXaGa
aiilaiaaicdaaiaawIcacaGLPaaaaaaabaGaamyAaiabgMGiplaado
haaeqaniabggHiLdGcdaqadaqaamaaeiaabaGaamiDaiabgkHiTiaa
d2gadaWgaaWcbaGaamyAaaqabaaakiaawIa7aiaaysW7caWG4bWaaS
baaSqaaiaadMgaaeqaaaGccaGLOaGaayzkaaGabmyBayaagaWaaSba
aSqaaiaadMgaaeqaaOGaaGjbVpaabmaabaWaaabuaeaacaWG3bWaaS
baaSqaaiaadMgacaaISaGaamOAaaqabaaabaGaamOAaiabgIGiolaa
dohaaeqaniabggHiLdGcdaaeqbqaaiaadEhadaWgaaWcbaGaamOAai
aaiYcacaWGRbaabeaakmaabmaabaGaamiEamaaBaaaleaacaWGRbaa
beaakiabgkHiTiaadIhadaWgaaWcbaGaamOAaaqabaaakiaawIcaca
GLPaaadaahaaWcbeqaaiaaikdaaaaabaGaam4AaiabgIGiolaadoha
aeqaniabggHiLdGccqGHsisldaaeqbqaaiaadEhadaWgaaWcbaGaam
yAaiaaiYcacaWGRbaabeaakmaabmaabaGaamiEamaaBaaaleaacaWG
RbaabeaakiabgkHiTiaadIhadaWgaaWcbaGaamyAaaqabaaakiaawI
cacaGLPaaadaahaaWcbeqaaiaaikdaaaaabaGaam4AaiabgIGiolaa
dohaaeqaniabggHiLdaakiaawIcacaGLPaaacqGHRaWkcaWGVbWaae
WaaeaacqaH7oaBdaahaaWcbeqaaiaaikdaaaaakiaawIcacaGLPaaa
aeaaaeaacaaI9aGaam4BamaabmaabaGaeq4UdW2aaWbaaSqabeaaca
aIYaaaaaGccaGLOaGaayzkaaGaaGOlaaaaaaa@DA60@
Considérons enfin
C
3
.
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWGdbWaaS
baaSqaaiaaiodaaeqaaOGaaiOlaaaa@3A5E@
Notons que, d’après (A.2) et
(A.3),
E
(
d
i
,
j
2
)
=
∑
k
∈
s
(
w
j
,
k
−
w
i
,
k
)
2
σ
k
2
+
O
i
,
j
(
λ
4
+
(
n
λ
)
−
2
)
(
A
.6
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWGfbWaae
WaaeaacaWGKbWaa0baaSqaaiaadMgacaaISaGaamOAaaqaaiaaikda
aaaakiaawIcacaGLPaaacaaI9aWaaabuaeaadaqadaqaaiaadEhada
WgaaWcbaGaamOAaiaaiYcacaWGRbaabeaakiabgkHiTiaadEhadaWg
aaWcbaGaamyAaiaaiYcacaWGRbaabeaaaOGaayjkaiaawMcaamaaCa
aaleqabaGaaGOmaaaakiabeo8aZnaaDaaaleaacaWGRbaabaGaaGOm
aaaaaeaacaWGRbGaeyicI4Saam4Caaqab0GaeyyeIuoakiabgUcaRi
aad+eadaWgaaWcbaGaamyAaiaaiYcacaWGQbaabeaakmaabmaabaGa
eq4UdW2aaWbaaSqabeaacaaI0aaaaOGaey4kaSYaaeWaaeaacaWGUb
Gaeq4UdWgacaGLOaGaayzkaaWaaWbaaSqabeaacqGHsislcaaIYaaa
aaGccaGLOaGaayzkaaGaaGzbVlaaywW7caaMf8UaaGzbVlaaywW7ca
GGOaGaaiyqaiaac6cacaaI2aGaaiykaaaa@6E92@
d’où
C
3
=
1
2
N
∑
i
∉
s
∑
j
∈
s
w
i
,
j
G
(
2
,
0
)
(
t
−
m
i
|
x
j
)
∑
k
∈
s
(
w
j
,
k
−
w
i
,
k
)
2
σ
k
2
+
O
(
λ
4
+
(
n
λ
)
−
2
)
=
1
2
N
∑
i
∉
s
G
(
2
,
0
)
(
t
−
m
i
|
x
i
)
σ
i
2
∑
j
∈
s
w
i
,
j
∑
k
∈
s
(
w
j
,
k
−
w
i
,
k
)
2
+
o
(
(
n
λ
)
−
1
)
+
O
(
λ
4
)
=
1
n
λ
N
−
n
N
κ
−
θ
μ
0
2
∫
a
b
G
(
2
,
0
)
(
t
−
m
(
x
)
|
x
)
σ
2
(
x
)
[
h
s
¯
(
x
)
/
h
s
(
x
)
]
d
x
+
o
(
(
n
λ
)
−
1
)
+
O
(
λ
4
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrViFfea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaafaqaaeWaca
aabaGaam4qamaaBaaaleaacaaIZaaabeaaaOqaaiaai2dadaWcaaqa
aiaaigdaaeaacaaIYaGaamOtaaaadaaeqbqabSqaaiaadMgacqGHji
YZcaWGZbaabeqdcqGHris5aOWaaabuaeaacaWG3bWaaSbaaSqaaiaa
dMgacaaISaGaamOAaaqabaGccaWGhbWaaWbaaSqabeaadaqadaqaai
aaikdacaGGSaGaaGimaaGaayjkaiaawMcaaaaaaeaacaWGQbGaeyic
I4Saam4Caaqab0GaeyyeIuoakmaabmaabaWaaqGaaeaacaWG0bGaey
OeI0IaamyBamaaBaaaleaacaWGPbaabeaaaOGaayjcSdGaaGjbVlaa
dIhadaWgaaWcbaGaamOAaaqabaaakiaawIcacaGLPaaadaaeqbqaam
aabmaabaGaam4DamaaBaaaleaacaWGQbGaaGilaiaadUgaaeqaaOGa
eyOeI0Iaam4DamaaBaaaleaacaWGPbGaaGilaiaadUgaaeqaaaGcca
GLOaGaayzkaaWaaWbaaSqabeaacaaIYaaaaOGaeq4Wdm3aa0baaSqa
aiaadUgaaeaacaaIYaaaaaqaaiaadUgacqGHiiIZcaWGZbaabeqdcq
GHris5aOGaey4kaSIaam4tamaabmaabaGaeq4UdW2aaWbaaSqabeaa
caaI0aaaaOGaey4kaSYaaeWaaeaacaWGUbGaeq4UdWgacaGLOaGaay
zkaaWaaWbaaSqabeaacqGHsislcaaIYaaaaaGccaGLOaGaayzkaaaa
baaabaGaaGypamaalaaabaGaaGymaaqaaiaaikdacaWGobaaamaaqa
fabaGaam4ramaaCaaaleqabaWaaeWaaeaacaaIYaGaaiilaiaaicda
aiaawIcacaGLPaaaaaaabaGaamyAaiabgMGiplaadohaaeqaniabgg
HiLdGcdaqadaqaamaaeiaabaGaamiDaiabgkHiTiaad2gadaWgaaWc
baGaamyAaaqabaaakiaawIa7aiaaysW7caWG4bWaaSbaaSqaaiaadM
gaaeqaaaGccaGLOaGaayzkaaGaeq4Wdm3aa0baaSqaaiaadMgaaeaa
caaIYaaaaOWaaabuaeaacaWG3bWaaSbaaSqaaiaadMgacaaISaGaam
OAaaqabaaabaGaamOAaiabgIGiolaadohaaeqaniabggHiLdGcdaae
qbqaamaabmaabaGaam4DamaaBaaaleaacaWGQbGaaGilaiaadUgaae
qaaOGaeyOeI0Iaam4DamaaBaaaleaacaWGPbGaaGilaiaadUgaaeqa
aaGccaGLOaGaayzkaaWaaWbaaSqabeaacaaIYaaaaaqaaiaadUgacq
GHiiIZcaWGZbaabeqdcqGHris5aOGaey4kaSIaam4BamaabmaabaWa
aeWaaeaacaWGUbGaeq4UdWgacaGLOaGaayzkaaWaaWbaaSqabeaacq
GHsislcaaIXaaaaaGccaGLOaGaayzkaaGaey4kaSIaam4tamaabmaa
baGaeq4UdW2aaWbaaSqabeaacaaI0aaaaaGccaGLOaGaayzkaaaaba
aabaGaaGypamaalaaabaGaaGymaaqaaiaad6gacqaH7oaBaaWaaSaa
aeaacaWGobGaeyOeI0IaamOBaaqaaiaad6eaaaWaaSaaaeaacqaH6o
WAcqGHsislcqaH4oqCaeaacqaH8oqBdaqhaaWcbaGaaGimaaqaaiaa
ikdaaaaaaOWaa8qmaeaacaWGhbWaaWbaaSqabeaadaqadaqaaiaaik
dacaGGSaGaaGimaaGaayjkaiaawMcaaaaaaeaacaWGHbaabaGaamOy
aaqdcqGHRiI8aOWaaeWaaeaadaabcaqaaiaadshacqGHsislcaWGTb
WaaeWaaeaacaWG4baacaGLOaGaayzkaaGaaGPaVdGaayjcSdGaaGjb
VlaadIhaaiaawIcacaGLPaaacqaHdpWCdaahaaWcbeqaaiaaikdaaa
GcdaqadaqaaiaadIhaaiaawIcacaGLPaaadaWadaqaamaalyaabaGa
amiAamaaBaaaleaacaaMc8Uabm4CayaaraaabeaakmaabmaabaGaam
iEaaGaayjkaiaawMcaaaqaaiaadIgadaWgaaWcbaGaam4CaaqabaGc
daqadaqaaiaadIhaaiaawIcacaGLPaaaaaaacaGLBbGaayzxaaGaam
izaiaadIhacqGHRaWkcaWGVbWaaeWaaeaadaqadaqaaiaad6gacqaH
7oaBaiaawIcacaGLPaaadaahaaWcbeqaaiabgkHiTiaaigdaaaaaki
aawIcacaGLPaaacqGHRaWkcaWGpbWaaeWaaeaacqaH7oaBdaahaaWc
beqaaiaaisdaaaaakiaawIcacaGLPaaaaaaaaa@0997@
avec
θ
:=
∫
−
1
1
K
(
v
)
∫
−
1
1
K
(
u
+
v
)
K
(
u
)
d
u
d
v
.
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacqaH4oqCca
aI6aGaaGypamaapedabaGaam4samaabmaabaGaamODaaGaayjkaiaa
wMcaaaWcbaGaeyOeI0IaaGymaaqaaiaaigdaa0Gaey4kIipakmaape
dabaGaam4samaabmaabaGaamyDaiabgUcaRiaadAhaaiaawIcacaGL
PaaacaWGlbWaaeWaaeaacaWG1baacaGLOaGaayzkaaGaamizaiaadw
hacaWGKbGaamODaaWcbaGaeyOeI0IaaGymaaqaaiaaigdaa0Gaey4k
Iipakiaac6caaaa@54AE@
En substituant les développements
susmentionnés à
C
1
,
C
2
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWGdbWaaS
baaSqaaiaaigdaaeqaaOGaaiilaiaadoeadaWgaaWcbaGaaGOmaaqa
baaaaa@3C0A@
et
C
3
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWGdbWaaS
baaSqaaiaaiodaaeqaaaaa@39A1@
dans (A.5), on obtient
finalement
E
(
F
^
*
(
t
)
−
F
N
(
t
)
)
=
λ
2
N
−
n
N
μ
2
μ
0
∫
a
b
G
(
0
,
2
)
(
t
−
m
(
x
)
|
x
)
h
s
¯
(
x
)
d
x
+
1
n
λ
N
−
n
N
[
K
(
0
)
−
κ
μ
0
∫
a
b
G
(
1
,
0
)
(
t
−
m
(
x
)
|
x
)
(
t
−
m
(
x
)
)
h
s
−
1
(
x
)
h
s
¯
(
x
)
d
x
+
κ
−
θ
μ
0
2
∫
a
b
G
(
2
,
0
)
(
t
−
m
(
x
)
|
x
)
σ
2
(
x
)
h
s
−
1
(
x
)
h
s
¯
(
x
)
d
x
]
+
o
(
λ
2
+
(
n
λ
)
−
1
)
.
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrFjpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaafaqaaeabca
aaaeaacaWGfbWaaeWaaeaaceWGgbGbaKaadaahaaWcbeqaaiaaiQca
aaGccaaMb8+aaeWaaeaacaWG0baacaGLOaGaayzkaaGaeyOeI0Iaam
OramaaBaaaleaacaWGobaabeaakmaabmaabaGaamiDaaGaayjkaiaa
wMcaaaGaayjkaiaawMcaaaqaaiaai2dacqaH7oaBdaahaaWcbeqaai
aaikdaaaGcdaWcaaqaaiaad6eacqGHsislcaWGUbaabaGaamOtaaaa
daWcaaqaaiabeY7aTnaaBaaaleaacaaIYaaabeaaaOqaaiabeY7aTn
aaBaaaleaacaaIWaaabeaaaaGcdaWdXaqaaiaadEeadaahaaWcbeqa
amaabmaabaGaaGimaiaacYcacaaIYaaacaGLOaGaayzkaaaaaaqaai
aadggaaeaacaWGIbaaniabgUIiYdGcdaqadaqaamaaeiaabaGaamiD
aiabgkHiTiaad2gadaqadaqaaiaadIhaaiaawIcacaGLPaaacaaMc8
oacaGLiWoacaaMe8UaamiEaaGaayjkaiaawMcaaiaadIgadaWgaaWc
baGaaGPaVlqadohagaqeaaqabaGcdaqadaqaaiaadIhaaiaawIcaca
GLPaaacaWGKbGaamiEaaqaaaqaaiaaysW7caaMe8Uaey4kaSYaaSaa
aeaacaaIXaaabaGaamOBaiabeU7aSbaadaWcaaqaaiaad6eacqGHsi
slcaWGUbaabaGaamOtaaaadaWabaqaamaalaaabaGaam4samaabmaa
baGaaGimaaGaayjkaiaawMcaaiabgkHiTiabeQ7aRbqaaiabeY7aTn
aaBaaaleaacaaIWaaabeaaaaGcdaWdXaqabSqaaiaadggaaeaacaWG
IbaaniabgUIiYdGccaWGhbWaaWbaaSqabeaadaqadaqaaiaaigdaca
GGSaGaaGimaaGaayjkaiaawMcaaaaakmaabmaabaWaaqGaaeaacaWG
0bGaeyOeI0IaamyBamaabmaabaGaamiEaaGaayjkaiaawMcaaiaayk
W7aiaawIa7aiaaysW7caWG4baacaGLOaGaayzkaaWaaeWaaeaacaWG
0bGaeyOeI0IaamyBamaabmaabaGaamiEaaGaayjkaiaawMcaaaGaay
jkaiaawMcaaiaadIgadaqhaaWcbaGaam4CaaqaaiabgkHiTiaaigda
aaGcdaqadaqaaiaadIhaaiaawIcacaGLPaaacaWGObWaaSbaaSqaai
aaykW7ceWGZbGbaebaaeqaaOWaaeWaaeaacaWG4baacaGLOaGaayzk
aaGaamizaiaadIhaaiaawUfaaaqaaaqaaiaaysW7caaMe8UaaGjbVl
aaysW7caaMe8UaaGjbVlaaysW7caaMe8UaaGjbVlaaysW7caaMe8Ua
aGjbVlaaysW7caaMe8UaaGjbVlaaysW7caaMe8UaaGjbVlaaysW7ca
aMe8UaaGjbVlaaysW7daWacaqaaiabgUcaRmaalaaabaGaeqOUdSMa
eyOeI0IaeqiUdehabaGaeqiVd02aa0baaSqaaiaaicdaaeaacaaIYa
aaaaaakmaapedabaGaam4ramaaCaaaleqabaWaaeWaaeaacaaIYaGa
aiilaiaaicdaaiaawIcacaGLPaaaaaaabaGaamyyaaqaaiaadkgaa0
Gaey4kIipakmaabmaabaWaaqGaaeaacaWG0bGaeyOeI0IaamyBamaa
bmaabaGaamiEaaGaayjkaiaawMcaaiaaykW7aiaawIa7aiaaysW7ca
WG4baacaGLOaGaayzkaaGaeq4Wdm3aaWbaaSqabeaacaaIYaaaaOWa
aeWaaeaacaWG4baacaGLOaGaayzkaaGaamiAamaaDaaaleaacaWGZb
aabaGaeyOeI0IaaGymaaaakmaabmaabaGaamiEaaGaayjkaiaawMca
aiaadIgadaWgaaWcbaGaaGPaVlqadohagaqeaaqabaGcdaqadaqaai
aadIhaaiaawIcacaGLPaaacaWGKbGaamiEaaGaayzxaaaabaaabaGa
aGzbVlabgUcaRiaad+gadaqadaqaaiabeU7aSnaaCaaaleqabaGaaG
OmaaaakiabgUcaRmaabmaabaGaamOBaiabeU7aSbGaayjkaiaawMca
amaaCaaaleqabaGaeyOeI0IaaGymaaaaaOGaayjkaiaawMcaaiaai6
caaaaaaa@121D@
Biais de l’estimateur
par la différence généralisée avec valeurs prédites modifiées
Soit
d
˜
i
,
j
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaaceWGKbGbaG
aadaWgaaWcbaGaamyAaiaaiYcacaWGQbaabeaaaaa@3BA8@
l’équivalent pondéré selon le
plan de sondage de
d
i
,
j
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWGKbWaaS
baaSqaaiaadMgacaaISaGaamOAaaqabaaaaa@3B99@
et observons que
F
˜
*
(
t
)
−
F
N
(
t
)
=
1
N
[
∑
i
∉
s
∑
j
∈
s
w
˜
i
,
j
(
I
(
ε
j
≤
t
−
m
i
+
d
˜
i
,
j
)
−
I
(
y
i
≤
t
)
)
+
∑
i
∈
s
(
1
−
π
i
−
1
)
∑
j
∈
s
w
˜
i
,
j
(
I
(
ε
j
≤
t
−
m
i
+
d
˜
i
,
j
)
−
I
(
y
i
≤
t
)
)
]
.
(
A
.7
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrFjpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaafaqaaeGaca
aabaGabmOrayaaiaWaaWbaaSqabeaacaaIQaaaaOWaaeWaaeaacaWG
0baacaGLOaGaayzkaaGaeyOeI0IaamOramaaBaaaleaacaWGobaabe
aakmaabmaabaGaamiDaaGaayjkaiaawMcaaaqaaiaai2dadaWcaaqa
aiaaigdaaeaacaWGobaaamaadeaabaWaaabuaeqaleaacaWGPbGaey
ycI8Saam4Caaqab0GaeyyeIuoakmaaqafabaGabm4DayaaiaWaaSba
aSqaaiaadMgacaaISaGaamOAaaqabaaabaGaamOAaiabgIGiolaado
haaeqaniabggHiLdGcdaqadaqaaiaadMeadaqadaqaaiabew7aLnaa
BaaaleaacaWGQbaabeaakiabgsMiJkaadshacqGHsislcaWGTbWaaS
baaSqaaiaadMgaaeqaaOGaey4kaSIabmizayaaiaWaaSbaaSqaaiaa
dMgacaaISaGaamOAaaqabaaakiaawIcacaGLPaaacqGHsislcaWGjb
WaaeWaaeaacaWG5bWaaSbaaSqaaiaadMgaaeqaaOGaeyizImQaamiD
aaGaayjkaiaawMcaaaGaayjkaiaawMcaaaGaay5waaaabaaabaGaaG
jbVlaaysW7caaMe8UaaGjbVlaaysW7caaMe8UaaGjbVpaadiaabaGa
ey4kaSYaaabuaeqaleaacaWGPbGaeyicI4Saam4Caaqab0GaeyyeIu
oakmaabmaabaGaaGymaiabgkHiTiabec8aWnaaDaaaleaacaWGPbaa
baGaeyOeI0IaaGymaaaaaOGaayjkaiaawMcaamaaqafabaGabm4Day
aaiaWaaSbaaSqaaiaadMgacaaISaGaamOAaaqabaaabaGaamOAaiab
gIGiolaadohaaeqaniabggHiLdGcdaqadaqaaiaadMeadaqadaqaai
abew7aLnaaBaaaleaacaWGQbaabeaakiabgsMiJkaadshacqGHsisl
caWGTbWaaSbaaSqaaiaadMgaaeqaaOGaey4kaSIabmizayaaiaWaaS
baaSqaaiaadMgacaaISaGaamOAaaqabaaakiaawIcacaGLPaaacqGH
sislcaWGjbWaaeWaaeaacaWG5bWaaSbaaSqaaiaadMgaaeqaaOGaey
izImQaamiDaaGaayjkaiaawMcaaaGaayjkaiaawMcaaaGaayzxaaGa
aGOlaaaacaaMf8UaaGzbVlaacIcacaGGbbGaaiOlaiaaiEdacaGGPa
aaaa@B0D9@
En adaptant la preuve qui mène à (A.4), on voit que le
développement asymptotique en (A.4) est également vérifié en prenant
d
˜
i
,
j
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaaceWGKbGbaG
aadaWgaaWcbaGaamyAaiaaiYcacaWGQbaabeaaaaa@3BA8@
à la place de
d
i
,
j
.
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWGKbWaaS
baaSqaaiaadMgacaaISaGaamOAaaqabaGccaGGUaaaaa@3C55@
L’adaptation de la partie
restante de la preuve mène en bout de ligne à
E
(
F
˜
*
(
t
)
−
F
N
(
t
)
)
=
λ
2
N
−
n
N
μ
2
μ
0
∫
a
b
G
(
0
,
2
)
(
t
−
m
(
x
)
|
x
)
h
(
x
)
d
x
+
1
n
λ
N
−
n
N
[
K
(
0
)
−
κ
μ
0
∫
a
b
G
(
1
,
0
)
(
t
−
m
(
x
)
|
x
)
(
t
−
m
(
x
)
)
h
s
−
1
(
x
)
h
(
x
)
d
x
+
κ
−
θ
μ
0
2
∫
a
b
G
(
2
,
0
)
(
t
−
m
(
x
)
|
x
)
σ
2
(
x
)
h
s
−
1
(
x
)
h
(
x
)
d
x
]
+
o
(
λ
2
+
(
n
λ
)
−
1
)
,
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrFjpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaafaqaaeabca
aaaeaacaWGfbWaaeWaaeaaceWGgbGbaGaadaahaaWcbeqaaiaaiQca
aaGccaaMb8+aaeWaaeaacaWG0baacaGLOaGaayzkaaGaeyOeI0Iaam
OramaaBaaaleaacaWGobaabeaakmaabmaabaGaamiDaaGaayjkaiaa
wMcaaaGaayjkaiaawMcaaaqaaiaai2dacqaH7oaBdaahaaWcbeqaai
aaikdaaaGcdaWcaaqaaiaad6eacqGHsislcaWGUbaabaGaamOtaaaa
daWcaaqaaiabeY7aTnaaBaaaleaacaaIYaaabeaaaOqaaiabeY7aTn
aaBaaaleaacaaIWaaabeaaaaGcdaWdXaqabSqaaiaadggaaeaacaWG
IbaaniabgUIiYdGccaWGhbWaaWbaaSqabeaadaqadaqaaiaaicdaca
GGSaGaaGOmaaGaayjkaiaawMcaaaaakmaabmaabaWaaqGaaeaacaWG
0bGaeyOeI0IaamyBamaabmaabaGaamiEaaGaayjkaiaawMcaaiaayk
W7aiaawIa7aiaaysW7caWG4baacaGLOaGaayzkaaGaamiAamaabmaa
baGaamiEaaGaayjkaiaawMcaaiaadsgacaWG4baabaaabaGaaGjbVl
aaysW7cqGHRaWkdaWcaaqaaiaaigdaaeaacaWGUbGaeq4UdWgaamaa
laaabaGaamOtaiabgkHiTiaad6gaaeaacaWGobaaamaadeaabaWaaS
aaaeaacaWGlbWaaeWaaeaacaaIWaaacaGLOaGaayzkaaGaeyOeI0Ia
eqOUdSgabaGaeqiVd02aaSbaaSqaaiaaicdaaeqaaaaakmaapedabe
WcbaGaamyyaaqaaiaadkgaa0Gaey4kIipakiaadEeadaahaaWcbeqa
amaabmaabaGaaGymaiaacYcacaaIWaaacaGLOaGaayzkaaaaaOWaae
WaaeaadaabcaqaaiaadshacqGHsislcaWGTbWaaeWaaeaacaWG4baa
caGLOaGaayzkaaGaaGPaVdGaayjcSdGaaGjbVlaadIhaaiaawIcaca
GLPaaadaqadaqaaiaadshacqGHsislcaWGTbWaaeWaaeaacaWG4baa
caGLOaGaayzkaaaacaGLOaGaayzkaaGaamiAamaaDaaaleaacaWGZb
aabaGaeyOeI0IaaGymaaaakmaabmaabaGaamiEaaGaayjkaiaawMca
aiaadIgadaqadaqaaiaadIhaaiaawIcacaGLPaaacaWGKbGaamiEaa
Gaay5waaaabaaabaGaaGjbVlaaysW7caaMe8UaaGjbVlaaysW7caaM
e8UaaGjbVlaaysW7caaMe8UaaGjbVlaaysW7caaMe8UaaGjbVlaays
W7caaMe8UaaGjbVlaaysW7caaMe8UaaGjbVpaadiaabaGaey4kaSYa
aSaaaeaacqaH6oWAcqGHsislcqaH4oqCaeaacqaH8oqBdaqhaaWcba
GaaGimaaqaaiaaikdaaaaaaOWaa8qmaeqaleaacaWGHbaabaGaamOy
aaqdcqGHRiI8aOGaam4ramaaCaaaleqabaWaaeWaaeaacaaIYaGaai
ilaiaaicdaaiaawIcacaGLPaaaaaGcdaqadaqaamaaeiaabaGaamiD
aiabgkHiTiaad2gadaqadaqaaiaadIhaaiaawIcacaGLPaaacaaMc8
oacaGLiWoacaaMe8UaamiEaaGaayjkaiaawMcaaiabeo8aZnaaCaaa
leqabaGaaGOmaaaakmaabmaabaGaamiEaaGaayjkaiaawMcaaiaadI
gadaqhaaWcbaGaam4CaaqaaiabgkHiTiaaigdaaaGcdaqadaqaaiaa
dIhaaiaawIcacaGLPaaacaWGObWaaeWaaeaacaWG4baacaGLOaGaay
zkaaGaamizaiaadIhaaiaaw2faaaqaaaqaaiaaysW7caaMe8Uaey4k
aSIaam4BamaabmaabaGaeq4UdW2aaWbaaSqabeaacaaIYaaaaOGaey
4kaSYaaeWaaeaacaWGUbGaeq4UdWgacaGLOaGaayzkaaWaaWbaaSqa
beaacqGHsislcaaIXaaaaaGccaGLOaGaayzkaaGaaGilaaaaaaa@06B8@
où
h
(
x
)
:=
h
s
¯
(
x
)
+
(
1
−
π
−
1
(
x
)
)
h
s
(
x
)
.
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWGObWaae
WaaeaacaWG4baacaGLOaGaayzkaaGaaGOoaiaai2dacaWGObWaaSba
aSqaaiaaykW7ceWGZbGbaebaaeqaaOWaaeWaaeaacaWG4baacaGLOa
GaayzkaaGaey4kaSYaaeWaaeaacaaIXaGaeyOeI0IaeqiWda3aaWba
aSqabeaacqGHsislcaaIXaaaaOWaaeWaaeaacaWG4baacaGLOaGaay
zkaaaacaGLOaGaayzkaaGaamiAamaaBaaaleaacaWGZbaabeaakmaa
bmaabaGaamiEaaGaayjkaiaawMcaaiaai6caaaa@52C0@
Variance de
l’estimateur fondé sur le modèle avec valeurs prédites modifiées
Écrivons
F
^
*
(
t
)
−
F
N
(
t
)
=
1
N
(
∑
i
∉
s
∑
j
∈
s
w
i
,
j
I
(
ε
j
≤
t
−
m
i
+
d
i
,
j
)
−
∑
i
∉
s
I
(
ε
i
≤
t
−
m
i
)
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaaceWGgbGbaK
aadaahaaWcbeqaaiaaiQcaaaGccaaMb8+aaeWaaeaacaWG0baacaGL
OaGaayzkaaGaeyOeI0IaamOramaaBaaaleaacaWGobaabeaakmaabm
aabaGaamiDaaGaayjkaiaawMcaaiaai2dadaWcaaqaaiaaigdaaeaa
caWGobaaamaabmaabaWaaabuaeqaleaacaWGPbGaeyycI8Saam4Caa
qab0GaeyyeIuoakmaaqafabaGaam4DamaaBaaaleaacaWGPbGaaGil
aiaadQgaaeqaaOGaamysaaWcbaGaamOAaiabgIGiolaadohaaeqani
abggHiLdGcdaqadaqaaiabew7aLnaaBaaaleaacaWGQbaabeaakiab
gsMiJkaadshacqGHsislcaWGTbWaaSbaaSqaaiaadMgaaeqaaOGaey
4kaSIaamizamaaBaaaleaacaWGPbGaaGilaiaadQgaaeqaaaGccaGL
OaGaayzkaaGaeyOeI0YaaabuaeaacaWGjbWaaeWaaeaacqaH1oqzda
WgaaWcbaGaamyAaaqabaGccqGHKjYOcaWG0bGaeyOeI0IaamyBamaa
BaaaleaacaWGPbaabeaaaOGaayjkaiaawMcaaaWcbaGaamyAaiabgM
GiplaadohaaeqaniabggHiLdaakiaawIcacaGLPaaaaaa@76AB@
et observons que
var
(
F
^
*
(
t
)
−
F
N
(
t
)
)
=
D
1
+
D
2
+
D
3
,
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaqG2bGaae
yyaiaabkhadaqadaqaaiqadAeagaqcamaaCaaaleqabaGaaGOkaaaa
kiaaygW7daqadaqaaiaadshaaiaawIcacaGLPaaacqGHsislcaWGgb
WaaSbaaSqaaiaad6eaaeqaaOWaaeWaaeaacaWG0baacaGLOaGaayzk
aaaacaGLOaGaayzkaaGaaGypaiaadseadaWgaaWcbaGaaGymaaqaba
GccqGHRaWkcaWGebWaaSbaaSqaaiaaikdaaeqaaOGaey4kaSIaamir
amaaBaaaleaacaaIZaaabeaakiaaiYcaaaa@4FD2@
où
D
1
:=
1
N
2
∑
i
1
∉
s
∑
i
2
∉
s
∑
j
∈
s
w
i
1
,
j
w
i
2
,
j
cov
(
I
(
ε
j
≤
t
−
m
i
1
+
d
i
1
,
j
)
,
I
(
ε
j
≤
t
−
m
i
2
+
d
i
2
,
j
)
)
,
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWGebWaaS
baaSqaaiaaigdaaeqaaOGaaGOoaiaai2dadaWcaaqaaiaaigdaaeaa
caWGobWaaWbaaSqabeaacaaIYaaaaaaakmaaqafabaWaaabuaeaada
aeqbqaaiaadEhadaWgaaWcbaGaamyAamaaBaaameaacaaIXaaabeaa
liaaiYcacaWGQbaabeaakiaadEhadaWgaaWcbaGaamyAamaaBaaame
aacaaIYaaabeaaliaaiYcacaWGQbaabeaaaeaacaWGQbGaeyicI4Sa
am4Caaqab0GaeyyeIuoaaSqaaiaadMgadaWgaaadbaGaaGOmaaqaba
WccqGHjiYZcaWGZbaabeqdcqGHris5aaWcbaGaamyAamaaBaaameaa
caaIXaaabeaaliabgMGiplaadohaaeqaniabggHiLdGcciGGJbGaai
4BaiaacAhadaqadaqaaiaadMeadaqadaqaaiabew7aLnaaBaaaleaa
caWGQbaabeaakiabgsMiJkaadshacqGHsislcaWGTbWaaSbaaSqaai
aadMgadaWgaaadbaGaaGymaaqabaaaleqaaOGaey4kaSIaamizamaa
BaaaleaacaWGPbWaaSbaaWqaaiaaigdaaeqaaSGaaGilaiaadQgaae
qaaaGccaGLOaGaayzkaaGaaGilaiaadMeadaqadaqaaiabew7aLnaa
BaaaleaacaWGQbaabeaakiabgsMiJkaadshacqGHsislcaWGTbWaaS
baaSqaaiaadMgadaWgaaadbaGaaGOmaaqabaaaleqaaOGaey4kaSIa
amizamaaBaaaleaacaWGPbWaaSbaaWqaaiaaikdaaeqaaSGaaGilai
aadQgaaeqaaaGccaGLOaGaayzkaaaacaGLOaGaayzkaaGaaGilaaaa
@8228@
D
2
:=
1
N
2
∑
i
1
∉
s
∑
i
2
∉
s
∑
j
1
∈
s
∑
j
2
∈
s
,
j
2
≠
j
1
w
i
1
,
j
1
w
i
2
,
j
2
×
cov
(
I
(
ε
j
1
≤
t
−
m
i
1
+
d
i
1
,
j
1
)
,
I
(
ε
j
2
≤
t
−
m
i
2
+
d
i
2
,
j
2
)
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWGebWaaS
baaSqaaiaaikdaaeqaaOGaaGOoaiaai2dadaWcaaqaaiaaigdaaeaa
caWGobWaaWbaaSqabeaacaaIYaaaaaaakmaaqafabaWaaabuaeaada
aeqbqaamaaqafabaGaam4DamaaBaaaleaacaWGPbWaaSbaaWqaaiaa
igdaaeqaaSGaaGilaiaadQgadaWgaaadbaGaaGymaaqabaaaleqaaO
Gaam4DamaaBaaaleaacaWGPbWaaSbaaWqaaiaaikdaaeqaaSGaaGil
aiaadQgadaWgaaadbaGaaGOmaaqabaaaleqaaaqaaiaadQgadaWgaa
adbaGaaGOmaaqabaWccqGHiiIZcaWGZbGaaGilaiaadQgadaWgaaad
baGaaGOmaaqabaWccqGHGjsUcaWGQbWaaSbaaWqaaiaaigdaaeqaaa
WcbeqdcqGHris5aaWcbaGaamOAamaaBaaameaacaaIXaaabeaaliab
gIGiolaadohaaeqaniabggHiLdaaleaacaWGPbWaaSbaaWqaaiaaik
daaeqaaSGaeyycI8Saam4Caaqab0GaeyyeIuoaaSqaaiaadMgadaWg
aaadbaGaaGymaaqabaWccqGHjiYZcaWGZbaabeqdcqGHris5aOGaey
41aqRaae4yaiaab+gacaqG2bWaaeWaaeaacaWGjbWaaeWaaeaacqaH
1oqzdaWgaaWcbaGaamOAamaaBaaameaacaaIXaaabeaaaSqabaGccq
GHKjYOcaWG0bGaeyOeI0IaamyBamaaBaaaleaacaWGPbWaaSbaaWqa
aiaaigdaaeqaaaWcbeaakiabgUcaRiaadsgadaWgaaWcbaGaamyAam
aaBaaameaacaaIXaaabeaaliaaiYcacaWGQbWaaSbaaWqaaiaaigda
aeqaaaWcbeaaaOGaayjkaiaawMcaaiaaiYcacaWGjbWaaeWaaeaacq
aH1oqzdaWgaaWcbaGaamOAamaaBaaameaacaaIYaaabeaaaSqabaGc
cqGHKjYOcaWG0bGaeyOeI0IaamyBamaaBaaaleaacaWGPbWaaSbaaW
qaaiaaikdaaeqaaaWcbeaakiabgUcaRiaadsgadaWgaaWcbaGaamyA
amaaBaaameaacaaIYaaabeaaliaaiYcacaWGQbWaaSbaaWqaaiaaik
daaeqaaaWcbeaaaOGaayjkaiaawMcaaaGaayjkaiaawMcaaaaa@96F1@
et où
D
3
:=
A
2
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWGebWaaS
baaSqaaiaaiodaaeqaaOGaaGOoaiaai2dacaWGbbWaaSbaaSqaaiaa
ikdaaeqaaaaa@3CE6@
provenant de la variance de
l’estimateur fondé sur le modèle de Kuo.
Considérons
D
1
.
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWGebWaaS
baaSqaaiaaigdaaeqaaOGaaiOlaaaa@3A5D@
Observons que
cov
(
I
(
ε
j
≤
t
−
m
i
1
+
d
i
1
,
j
)
,
I
(
ε
j
≤
t
−
m
i
2
+
d
i
2
,
j
)
)
=
E
(
G
(
t
−
m
i
1
+
d
i
1
,
j
∧
t
−
m
i
2
+
d
i
2
,
j
|
x
j
)
)
−
E
(
G
(
t
−
m
i
1
+
d
i
1
,
j
|
x
j
)
)
E
(
G
(
t
−
m
i
2
+
d
i
2
,
j
|
x
j
)
)
.
(
A
.8
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpu0de9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0dXxbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaqbaeaabiGaaa
qaaiaabogacaqGVbGaaeODamaabmaabaGaamysamaabmaabaGaeqyT
du2aaSbaaSqaaiaadQgaaeqaaOGaeyizImQaamiDaiabgkHiTiaad2
gadaWgaaWcbaGaamyAamaaBaaameaacaaIXaaabeaaaSqabaGccqGH
RaWkcaWGKbWaaSbaaSqaaiaadMgadaWgaaadbaGaaGymaaqabaWcca
aISaGaamOAaaqabaaakiaawIcacaGLPaaacaaISaGaamysamaabmaa
baGaeqyTdu2aaSbaaSqaaiaadQgaaeqaaOGaeyizImQaamiDaiabgk
HiTiaad2gadaWgaaWcbaGaamyAamaaBaaameaacaaIYaaabeaaaSqa
baGccqGHRaWkcaWGKbWaaSbaaSqaaiaadMgadaWgaaadbaGaaGOmaa
qabaWccaaISaGaamOAaaqabaaakiaawIcacaGLPaaaaiaawIcacaGL
PaaaaeaacaaI9aGaamyramaabmaabaGaam4ramaabmaabaWaaqGaae
aacaWG0bGaeyOeI0IaamyBamaaBaaaleaacaWGPbWaaSbaaWqaaiaa
igdaaeqaaaWcbeaakiabgUcaRiaadsgadaWgaaWcbaGaamyAamaaBa
aameaacaaIXaaabeaaliaaiYcacaWGQbaabeaakiabgEIizlaadsha
cqGHsislcaWGTbWaaSbaaSqaaiaadMgadaWgaaadbaGaaGOmaaqaba
aaleqaaOGaey4kaSIaamizamaaBaaaleaacaWGPbWaaSbaaWqaaiaa
ikdaaeqaaSGaaGilaiaadQgaaeqaaaGccaGLiWoacaaMc8UaamiEam
aaBaaaleaacaWGQbaabeaaaOGaayjkaiaawMcaaaGaayjkaiaawMca
aaqaaaqaaiabgkHiTiaadweadaqadaqaaiaadEeadaqadaqaamaaei
aabaGaamiDaiabgkHiTiaad2gadaWgaaWcbaGaamyAamaaBaaameaa
caaIXaaabeaaaSqabaGccqGHRaWkcaWGKbWaaSbaaSqaaiaadMgada
WgaaadbaGaaGymaaqabaWccaaISaGaamOAaaqabaaakiaawIa7aiaa
ykW7caWG4bWaaSbaaSqaaiaadQgaaeqaaaGccaGLOaGaayzkaaaaca
GLOaGaayzkaaGaamyramaabmaabaGaam4ramaabmaabaWaaqGaaeaa
caWG0bGaeyOeI0IaamyBamaaBaaaleaacaWGPbWaaSbaaWqaaiaaik
daaeqaaaWcbeaakiabgUcaRiaadsgadaWgaaWcbaGaamyAamaaBaaa
meaacaaIYaaabeaaliaaiYcacaWGQbaabeaaaOGaayjcSdGaaGPaVl
aadIhadaWgaaWcbaGaamOAaaqabaaakiaawIcacaGLPaaaaiaawIca
caGLPaaacaaIUaaaaiaacIcacaGGbbGaaiOlaiaaiIdacaGGPaaaaa@AC01@
Puisque
|
(
t
−
m
i
1
+
d
i
1
,
j
∧
t
−
m
i
2
+
d
i
2
,
j
)
−
(
t
−
m
i
1
∧
t
−
m
i
2
)
|
≤
|
d
i
1
,
j
|
+
|
d
i
2
,
j
|
,
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaadaabdaqaai
aaykW7daqadaqaaiaadshacqGHsislcaWGTbWaaSbaaSqaaiaadMga
daWgaaadbaGaaGymaaqabaaaleqaaOGaey4kaSIaamizamaaBaaale
aacaWGPbWaaSbaaWqaaiaaigdaaeqaaSGaaGilaiaadQgaaeqaaOGa
ey4jIKTaamiDaiabgkHiTiaad2gadaWgaaWcbaGaamyAamaaBaaame
aacaaIYaaabeaaaSqabaGccqGHRaWkcaWGKbWaaSbaaSqaaiaadMga
daWgaaadbaGaaGOmaaqabaWccaaISaGaamOAaaqabaaakiaawIcaca
GLPaaacqGHsisldaqadaqaaiaadshacqGHsislcaWGTbWaaSbaaSqa
aiaadMgadaWgaaadbaGaaGymaaqabaaaleqaaOGaey4jIKTaamiDai
abgkHiTiaad2gadaWgaaWcbaGaamyAamaaBaaameaacaaIYaaabeaa
aSqabaaakiaawIcacaGLPaaacaaMc8oacaGLhWUaayjcSdGaeyizIm
6aaqWaaeaacaaMc8UaamizamaaBaaaleaacaWGPbWaaSbaaWqaaiaa
igdaaeqaaSGaaGilaiaadQgaaeqaaOGaaGPaVdGaay5bSlaawIa7ai
abgUcaRmaaemaabaGaaGPaVlaadsgadaWgaaWcbaGaamyAamaaBaaa
meaacaaIYaaabeaaliaaiYcacaWGQbaabeaakiaaykW7aiaawEa7ca
GLiWoacaaISaaaaa@7D58@
il découle de (A.6) que
E
(
G
(
t
−
m
i
1
+
d
i
1
,
j
∧
t
−
m
i
2
+
d
i
2
,
j
|
x
j
)
)
=
G
(
t
−
m
i
1
∧
t
−
m
i
2
|
x
j
)
+
O
i
1
,
i
2
,
j
(
λ
2
+
(
n
λ
)
−
1
/
2
)
.
(
A
.9
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWGfbWaae
WaaeaacaWGhbWaaeWaaeaadaabcaqaaiaadshacqGHsislcaWGTbWa
aSbaaSqaaiaadMgadaWgaaadbaGaaGymaaqabaaaleqaaOGaey4kaS
IaamizamaaBaaaleaacaWGPbWaaSbaaWqaaiaaigdaaeqaaSGaaGil
aiaadQgaaeqaaOGaey4jIKTaamiDaiabgkHiTiaad2gadaWgaaWcba
GaamyAamaaBaaameaacaaIYaaabeaaaSqabaGccqGHRaWkcaWGKbWa
aSbaaSqaaiaadMgadaWgaaadbaGaaGOmaaqabaWccaaISaGaamOAaa
qabaaakiaawIa7aiaaysW7caWG4bWaaSbaaSqaaiaadQgaaeqaaaGc
caGLOaGaayzkaaaacaGLOaGaayzkaaGaaGypaiaadEeadaqadaqaam
aaeiaabaGaamiDaiabgkHiTiaad2gadaWgaaWcbaGaamyAamaaBaaa
meaacaaIXaaabeaaaSqabaGccqGHNis2caWG0bGaeyOeI0IaamyBam
aaBaaaleaacaWGPbWaaSbaaWqaaiaaikdaaeqaaaWcbeaaaOGaayjc
SdGaaGjbVlaadIhadaWgaaWcbaGaamOAaaqabaaakiaawIcacaGLPa
aacqGHRaWkcaWGpbWaaSbaaSqaaiaadMgadaWgaaadbaGaaGymaaqa
baWccaaISaGaamyAamaaBaaameaacaaIYaaabeaaliaaiYcacaWGQb
aabeaakmaabmaabaGaeq4UdW2aaWbaaSqabeaacaaIYaaaaOGaey4k
aSYaaeWaaeaacaWGUbGaeq4UdWgacaGLOaGaayzkaaWaaWbaaSqabe
aacqGHsisldaWcgaqaaiaaigdaaeaacaaIYaaaaaaaaOGaayjkaiaa
wMcaaiaai6cacaaMf8UaaGzbVlaacIcacaGGbbGaaiOlaiaaiMdaca
GGPaaaaa@87CB@
En outre, de (A.1), (A.4) et (A.6),
il découle que
E (
G (
t −
m
i
+
d
i , j
|
x
j
)
) =
G (
t −
m
i
|
x
j
) +
O
i , j
(
λ
2
+
(
n λ
)
− 1 / 2
) .
( A .10 )
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpC0xe9LqFf0de9
vqaqFeFr0xbba9Fa0P0RWFb9fq0hXdbbb9=e0dfrpm0dXdirVu0=vr
0=vr0=fdbaqaaeGaciGaaiaabeqaamaabaabaaGcbaqbaeaabeGaaa
qaaiaadweadaqadaqaaiaadEeadaqadaqaamaaeiaabaGaamiDaiab
gkHiTiaad2gadaWgaaWcbaGaamyAaaqabaGccqGHRaWkcaWGKbWaaS
baaSqaaiaadMgacaaISaGaamOAaaqabaaakiaawIa7aiaaysW7caWG
4bWaaSbaaSqaaiaadQgaaeqaaaGccaGLOaGaayzkaaaacaGLOaGaay
zkaaGaaGjbVlabg2da9aqaaiaadEeadaqadaqaamaaeiaabaGaamiD
aiabgkHiTiaad2gadaWgaaWcbaGaamyAaaqabaaakiaawIa7aiaays
W7caWG4bWaaSbaaSqaaiaadQgaaeqaaaGccaGLOaGaayzkaaGaey4k
aSIaam4tamaaBaaaleaacaWGPbGaaGilaiaadQgaaeqaaOWaaeWaae
aacqaH7oaBdaahaaWcbeqaaiaaikdaaaGccqGHRaWkdaqadaqaaiaa
d6gacqaH7oaBaiaawIcacaGLPaaadaahaaWcbeqaaiabgkHiTmaaly
aabaGaaGymaaqaaiaaikdaaaaaaaGccaGLOaGaayzkaaGaaGOlaaaa
caaMf8UaaGzbVlaaywW7caaMf8UaaGzbVlaacIcacaGGbbGaaiOlai
aaigdacaaIWaGaaiykaaaa@72E5@
En utilisant (A.9) et (A.10) pour obtenir un
développement asymptotique pour la covariance en (A.8) et en introduisant par
substitution le résultat dans la définition de
D
1
,
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWGebWaaS
baaSqaaiaaigdaaeqaaOGaaiilaaaa@3A5B@
on obtient
D
1
:=
1
N
2
∑
i
1
∉
s
∑
i
2
∉
s
∑
j
∈
s
w
i
1
,
j
w
i
2
,
j
cov
(
I
(
ε
j
≤
t
−
m
i
1
+
d
i
1
,
j
)
,
I
(
ε
j
≤
t
−
m
i
2
+
d
i
2
,
j
)
)
=
1
N
2
∑
i
1
∉
s
∑
i
2
∉
s
∑
j
∈
s
w
i
1
,
j
w
i
2
,
j
[
E
(
G
(
t
−
m
i
1
+
d
i
1
,
j
∧
t
−
m
i
2
+
d
i
2
,
j
|
x
j
)
)
−
E
(
G
(
t
−
m
i
1
+
d
i
1
,
j
|
x
j
)
)
E
(
G
(
t
−
m
i
2
+
d
i
2
,
j
|
x
j
)
)
]
=
1
N
2
∑
i
1
∉
s
∑
i
2
∉
s
∑
j
∈
s
w
i
1
,
j
w
i
2
,
j
[
G
(
t
−
m
i
1
∧
t
−
m
i
2
|
x
j
)
−
G
(
t
−
m
i
1
|
x
j
)
G
(
t
−
m
i
2
|
x
j
)
]
+
O
(
λ
2
n
−
1
+
(
n
λ
)
−
1
/
2
n
−
1
)
=
1
N
2
∑
j
∈
s
[
G
(
t
−
m
j
|
x
j
)
−
G
2
(
t
−
m
j
|
x
j
)
]
(
∑
i
∉
s
w
i
,
j
)
2
+
O
(
λ
n
−
1
+
(
n
λ
)
−
1
/
2
n
−
1
)
=
1
n
(
N
−
n
N
)
2
∫
a
b
[
G
(
t
−
m
(
x
)
|
x
)
−
G
2
(
t
−
m
(
x
)
|
x
)
]
[
h
s
¯
(
x
)
/
h
s
(
x
)
]
h
s
¯
(
x
)
d
x
+
O
(
(
n
λ
)
−
1
α
+
n
−
1
λ
+
n
−
1
(
n
λ
)
−
1
/
2
)
.
(
A
.11
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaafaqaaeacca
aaaaqaaiaadseadaWgaaWcbaGaaGymaaqabaaakeaacaaI6aGaaGyp
amaalaaabaGaaGymaaqaaiaad6eadaahaaWcbeqaaiaaikdaaaaaaO
WaaabuaeaadaaeqbqaamaaqafabaGaam4DamaaBaaaleaacaWGPbWa
aSbaaWqaaiaaigdaaeqaaSGaaGilaiaadQgaaeqaaOGaam4DamaaBa
aaleaacaWGPbWaaSbaaWqaaiaaikdaaeqaaSGaaGilaiaadQgaaeqa
aaqaaiaadQgacqGHiiIZcaWGZbaabeqdcqGHris5aaWcbaGaamyAam
aaBaaameaacaaIYaaabeaaliabgMGiplaadohaaeqaniabggHiLdaa
leaacaWGPbWaaSbaaWqaaiaaigdaaeqaaSGaeyycI8Saam4Caaqab0
GaeyyeIuoakiaabogacaqGVbGaaeODamaabmaabaGaamysamaabmaa
baGaeqyTdu2aaSbaaSqaaiaadQgaaeqaaOGaeyizImQaamiDaiabgk
HiTiaad2gadaWgaaWcbaGaamyAamaaBaaameaacaaIXaaabeaaaSqa
baGccqGHRaWkcaWGKbWaaSbaaSqaaiaadMgadaWgaaadbaGaaGymaa
qabaWccaaISaGaamOAaaqabaaakiaawIcacaGLPaaacaaISaGaamys
amaabmaabaGaeqyTdu2aaSbaaSqaaiaadQgaaeqaaOGaeyizImQaam
iDaiabgkHiTiaad2gadaWgaaWcbaGaamyAamaaBaaameaacaaIYaaa
beaaaSqabaGccqGHRaWkcaWGKbWaaSbaaSqaaiaadMgadaWgaaadba
GaaGOmaaqabaWccaaISaGaamOAaaqabaaakiaawIcacaGLPaaaaiaa
wIcacaGLPaaaaeaaaeaacaaI9aWaaSaaaeaacaaIXaaabaGaamOtam
aaCaaaleqabaGaaGOmaaaaaaGcdaaeqbqaamaaqafabaWaaabuaeaa
caWG3bWaaSbaaSqaaiaadMgadaWgaaadbaGaaGymaaqabaWccaaISa
GaamOAaaqabaGccaWG3bWaaSbaaSqaaiaadMgadaWgaaadbaGaaGOm
aaqabaWccaaISaGaamOAaaqabaaabaGaamOAaiabgIGiolaadohaae
qaniabggHiLdaaleaacaWGPbWaaSbaaWqaaiaaikdaaeqaaSGaeyyc
I8Saam4Caaqab0GaeyyeIuoaaSqaaiaadMgadaWgaaadbaGaaGymaa
qabaWccqGHjiYZcaWGZbaabeqdcqGHris5aOWaamqaaeaacaWGfbWa
aeWaaeaacaWGhbWaaeWaaeaadaabcaqaaiaadshacqGHsislcaWGTb
WaaSbaaSqaaiaadMgadaWgaaadbaGaaGymaaqabaaaleqaaOGaey4k
aSIaamizamaaBaaaleaacaWGPbWaaSbaaWqaaiaaigdaaeqaaSGaaG
ilaiaadQgaaeqaaOGaey4jIKTaamiDaiabgkHiTiaad2gadaWgaaWc
baGaamyAamaaBaaameaacaaIYaaabeaaaSqabaGccqGHRaWkcaWGKb
WaaSbaaSqaaiaadMgadaWgaaadbaGaaGOmaaqabaWccaaISaGaamOA
aaqabaaakiaawIa7aiaaysW7caWG4bWaaSbaaSqaaiaadQgaaeqaaa
GccaGLOaGaayzkaaaacaGLOaGaayzkaaaacaGLBbaaaeaaaeaacaaM
e8UaaGjbVlaaysW7caaMe8UaaGjbVlaaysW7caaMe8UaaGjbVlaays
W7caaMe8UaaGjbVlaaysW7caaMe8UaaGjbVlaaysW7caaMe8UaaGjb
VlaaysW7caaMe8UaaGjbVlaaysW7caaMe8UaaGjbVlaaysW7caaMe8
UaaGjbVlaaysW7daWacaqaaiabgkHiTiaadweadaqadaqaaiaadEea
daqadaqaamaaeiaabaGaamiDaiabgkHiTiaad2gadaWgaaWcbaGaam
yAamaaBaaameaacaaIXaaabeaaaSqabaGccqGHRaWkcaWGKbWaaSba
aSqaaiaadMgadaWgaaadbaGaaGymaaqabaWccaaISaGaamOAaaqaba
aakiaawIa7aiaaysW7caWG4bWaaSbaaSqaaiaadQgaaeqaaaGccaGL
OaGaayzkaaaacaGLOaGaayzkaaGaamyramaabmaabaGaam4ramaabm
aabaWaaqGaaeaacaWG0bGaeyOeI0IaamyBamaaBaaaleaacaWGPbWa
aSbaaWqaaiaaikdaaeqaaaWcbeaakiabgUcaRiaadsgadaWgaaWcba
GaamyAamaaBaaameaacaaIYaaabeaaliaaiYcacaWGQbaabeaaaOGa
ayjcSdGaaGjbVlaadIhadaWgaaWcbaGaamOAaaqabaaakiaawIcaca
GLPaaaaiaawIcacaGLPaaaaiaaw2faaaqaaaqaaiaai2dadaWcaaqa
aiaaigdaaeaacaWGobWaaWbaaSqabeaacaaIYaaaaaaakmaaqafaba
WaaabuaeaadaaeqbqaaiaadEhadaWgaaWcbaGaamyAamaaBaaameaa
caaIXaaabeaaliaaiYcacaWGQbaabeaakiaadEhadaWgaaWcbaGaam
yAamaaBaaameaacaaIYaaabeaaliaaiYcacaWGQbaabeaaaeaacaWG
QbGaeyicI4Saam4Caaqab0GaeyyeIuoaaSqaaiaadMgadaWgaaadba
GaaGOmaaqabaWccqGHjiYZcaWGZbaabeqdcqGHris5aaWcbaGaamyA
amaaBaaameaacaaIXaaabeaaliabgMGiplaadohaaeqaniabggHiLd
GcdaWadaqaaiaadEeadaqadaqaamaaeiaabaGaamiDaiabgkHiTiaa
d2gadaWgaaWcbaGaamyAamaaBaaameaacaaIXaaabeaaaSqabaGccq
GHNis2caWG0bGaeyOeI0IaamyBamaaBaaaleaacaWGPbWaaSbaaWqa
aiaaikdaaeqaaaWcbeaaaOGaayjcSdGaaGjbVlaadIhadaWgaaWcba
GaamOAaaqabaaakiaawIcacaGLPaaacqGHsislcaWGhbWaaeWaaeaa
daabcaqaaiaadshacqGHsislcaWGTbWaaSbaaSqaaiaadMgadaWgaa
adbaGaaGymaaqabaaaleqaaaGccaGLiWoacaaMe8UaamiEamaaBaaa
leaacaWGQbaabeaaaOGaayjkaiaawMcaaiaadEeadaqadaqaamaaei
aabaGaamiDaiabgkHiTiaad2gadaWgaaWcbaGaamyAamaaBaaameaa
caaIYaaabeaaaSqabaaakiaawIa7aiaaysW7caWG4bWaaSbaaSqaai
aadQgaaeqaaaGccaGLOaGaayzkaaaacaGLBbGaayzxaaaabaaabaGa
aGjbVlaaysW7cqGHRaWkcaWGpbWaaeWaaeaacqaH7oaBdaahaaWcbe
qaaiaaikdaaaGccaWGUbWaaWbaaSqabeaacqGHsislcaaIXaaaaOGa
ey4kaSYaaeWaaeaacaWGUbGaeq4UdWgacaGLOaGaayzkaaWaaWbaaS
qabeaacqGHsisldaWcgaqaaiaaigdaaeaacaaIYaaaaaaakiaad6ga
daahaaWcbeqaaiabgkHiTiaaigdaaaaakiaawIcacaGLPaaaaeaaae
aacaaI9aWaaSaaaeaacaaIXaaabaGaamOtamaaCaaaleqabaGaaGOm
aaaaaaGcdaaeqbqaamaadmaabaGaam4ramaabmaabaWaaqGaaeaaca
WG0bGaeyOeI0IaamyBamaaBaaaleaacaWGQbaabeaaaOGaayjcSdGa
aGjbVlaadIhadaWgaaWcbaGaamOAaaqabaaakiaawIcacaGLPaaacq
GHsislcaWGhbWaaWbaaSqabeaacaaIYaaaaOWaaeWaaeaadaabcaqa
aiaadshacqGHsislcaWGTbWaaSbaaSqaaiaadQgaaeqaaaGccaGLiW
oacaaMe8UaamiEamaaBaaaleaacaWGQbaabeaaaOGaayjkaiaawMca
aaGaay5waiaaw2faaaWcbaGaamOAaiabgIGiolaadohaaeqaniabgg
HiLdGccaaMe8+aaeWaaeaadaaeqbqaaiaadEhadaWgaaWcbaGaamyA
aiaaiYcacaWGQbaabeaaaeaacaWGPbGaeyycI8Saam4Caaqab0Gaey
yeIuoaaOGaayjkaiaawMcaamaaCaaaleqabaGaaGOmaaaakiabgUca
Riaad+eadaqadaqaaiabeU7aSjaad6gadaahaaWcbeqaaiabgkHiTi
aaigdaaaGccqGHRaWkdaqadaqaaiaad6gacqaH7oaBaiaawIcacaGL
PaaadaahaaWcbeqaaiabgkHiTmaalyaabaGaaGymaaqaaiaaikdaaa
aaaOGaamOBamaaCaaaleqabaGaeyOeI0IaaGymaaaaaOGaayjkaiaa
wMcaaaqaaaqaaiaai2dadaWcaaqaaiaaigdaaeaacaWGUbaaamaabm
aabaWaaSaaaeaacaWGobGaeyOeI0IaamOBaaqaaiaad6eaaaaacaGL
OaGaayzkaaWaaWbaaSqabeaacaaIYaaaaOWaa8qmaeqaleaacaWGHb
aabaGaamOyaaqdcqGHRiI8aOWaamWaaeaacaWGhbWaaeWaaeaadaab
caqaaiaadshacqGHsislcaWGTbWaaeWaaeaacaWG4baacaGLOaGaay
zkaaGaaGPaVdGaayjcSdGaaGjbVlaadIhaaiaawIcacaGLPaaacqGH
sislcaWGhbWaaWbaaSqabeaacaaIYaaaaOWaaeWaaeaadaabcaqaai
aadshacqGHsislcaWGTbWaaeWaaeaacaWG4baacaGLOaGaayzkaaGa
aGPaVdGaayjcSdGaaGjbVlaadIhaaiaawIcacaGLPaaaaiaawUfaca
GLDbaacaaMe8+aamWaaeaadaWcgaqaaiaadIgadaWgaaWcbaGaaGPa
VlqadohagaqeaaqabaGcdaqadaqaaiaadIhaaiaawIcacaGLPaaaae
aacaWGObWaaSbaaSqaaiaadohaaeqaaOWaaeWaaeaacaWG4baacaGL
OaGaayzkaaaaaaGaay5waiaaw2faaiaadIgadaWgaaWcbaGaaGPaVl
qadohagaqeaaqabaGcdaqadaqaaiaadIhaaiaawIcacaGLPaaacaWG
KbGaamiEaaqaaaqaaiaaysW7caaMe8Uaey4kaSIaam4tamaabmaaba
WaaeWaaeaacaWGUbGaeq4UdWgacaGLOaGaayzkaaWaaWbaaSqabeaa
cqGHsislcaaIXaaaaOGaeqySdeMaey4kaSIaamOBamaaCaaaleqaba
GaeyOeI0IaaGymaaaakiabeU7aSjabgUcaRiaad6gadaahaaWcbeqa
aiabgkHiTiaaigdaaaGcdaqadaqaaiaad6gacqaH7oaBaiaawIcaca
GLPaaadaahaaWcbeqaaiabgkHiTmaalyaabaGaaGymaaqaaiaaikda
aaaaaaGccaGLOaGaayzkaaGaaGOlaaaacaaMf8UaaGzbVlaacIcaca
GGbbGaaiOlaiaaigdacaaIXaGaaiykaaaa@274A@
Considérons ensuite
D
2
:=
1
N
2
∑
i
1
∉
s
∑
i
2
∉
s
∑
j
1
∈
s
∑
j
2
∈
s
,
j
2
≠
j
1
w
i
1
,
j
1
w
i
2
,
j
2
×
cov
(
I
(
ε
j
1
≤
t
−
m
i
1
+
d
i
1
,
j
1
)
,
I
(
ε
j
2
≤
t
−
m
i
2
+
d
i
2
,
j
2
)
)
.
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWGebWaaS
baaSqaaiaaikdaaeqaaOGaaGOoaiaai2dadaWcaaqaaiaaigdaaeaa
caWGobWaaWbaaSqabeaacaaIYaaaaaaakmaaqafabaWaaabuaeaada
aeqbqaamaaqafabaGaam4DamaaBaaaleaacaWGPbWaaSbaaWqaaiaa
igdaaeqaaSGaaGilaiaadQgadaWgaaadbaGaaGymaaqabaaaleqaaO
Gaam4DamaaBaaaleaacaWGPbWaaSbaaWqaaiaaikdaaeqaaSGaaGil
aiaadQgadaWgaaadbaGaaGOmaaqabaaaleqaaaqaaiaadQgadaWgaa
adbaGaaGOmaaqabaWccqGHiiIZcaWGZbGaaGilaiaadQgadaWgaaad
baGaaGOmaaqabaWccqGHGjsUcaWGQbWaaSbaaWqaaiaaigdaaeqaaa
WcbeqdcqGHris5aaWcbaGaamOAamaaBaaameaacaaIXaaabeaaliab
gIGiolaadohaaeqaniabggHiLdaaleaacaWGPbWaaSbaaWqaaiaaik
daaeqaaSGaeyycI8Saam4Caaqab0GaeyyeIuoaaSqaaiaadMgadaWg
aaadbaGaaGymaaqabaWccqGHjiYZcaWGZbaabeqdcqGHris5aOGaey
41aqRaae4yaiaab+gacaqG2bWaaeWaaeaacaWGjbWaaeWaaeaacqaH
1oqzdaWgaaWcbaGaamOAamaaBaaameaacaaIXaaabeaaaSqabaGccq
GHKjYOcaWG0bGaeyOeI0IaamyBamaaBaaaleaacaWGPbWaaSbaaWqa
aiaaigdaaeqaaaWcbeaakiabgUcaRiaadsgadaWgaaWcbaGaamyAam
aaBaaameaacaaIXaaabeaaliaaiYcacaWGQbWaaSbaaWqaaiaaigda
aeqaaaWcbeaaaOGaayjkaiaawMcaaiaaiYcacaWGjbWaaeWaaeaacq
aH1oqzdaWgaaWcbaGaamOAamaaBaaameaacaaIYaaabeaaaSqabaGc
cqGHKjYOcaWG0bGaeyOeI0IaamyBamaaBaaaleaacaWGPbWaaSbaaW
qaaiaaikdaaeqaaaWcbeaakiabgUcaRiaadsgadaWgaaWcbaGaamyA
amaaBaaameaacaaIYaaabeaaliaaiYcacaWGQbWaaSbaaWqaaiaaik
daaeqaaaWcbeaaaOGaayjkaiaawMcaaaGaayjkaiaawMcaaiaai6ca
aaa@97A9@
Puisque
cov
(
I
(
ε
j
1
≤
t
−
m
i
1
+
d
i
1
,
j
1
)
,
I
(
ε
j
2
≤
t
−
m
i
2
+
d
i
2
,
j
2
)
)
=
0
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaqGJbGaae
4BaiaabAhadaqadaqaaiaadMeadaqadaqaaiabew7aLnaaBaaaleaa
caWGQbWaaSbaaWqaaiaaigdaaeqaaaWcbeaakiabgsMiJkaadshacq
GHsislcaWGTbWaaSbaaSqaaiaadMgadaWgaaadbaGaaGymaaqabaaa
leqaaOGaey4kaSIaamizamaaBaaaleaacaWGPbWaaSbaaWqaaiaaig
daaeqaaSGaaGilaiaadQgadaWgaaadbaGaaGymaaqabaaaleqaaaGc
caGLOaGaayzkaaGaaGilaiaadMeadaqadaqaaiabew7aLnaaBaaale
aacaWGQbWaaSbaaWqaaiaaikdaaeqaaaWcbeaakiabgsMiJkaadsha
cqGHsislcaWGTbWaaSbaaSqaaiaadMgadaWgaaadbaGaaGOmaaqaba
aaleqaaOGaey4kaSIaamizamaaBaaaleaacaWGPbWaaSbaaWqaaiaa
ikdaaeqaaSGaaGilaiaadQgadaWgaaadbaGaaGOmaaqabaaaleqaaa
GccaGLOaGaayzkaaaacaGLOaGaayzkaaGaaGypaiaaicdaaaa@64ED@
si
|
x
i
1
−
x
i
2
|
>
2
λ
,
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaadaabdaqaai
aaykW7caWG4bWaaSbaaSqaaiaadMgadaWgaaadbaGaaGymaaqabaaa
leqaaOGaeyOeI0IaamiEamaaBaaaleaacaWGPbWaaSbaaWqaaiaaik
daaeqaaaWcbeaakiaaykW7aiaawEa7caGLiWoacaaI+aGaaGOmaiab
eU7aSjaacYcaaaa@4927@
il s’ensuit que les termes de
reste
R
i
1
,
j
1
,
i
2
,
j
2
,
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWGsbWaaS
baaSqaaiaadMgadaWgaaadbaGaaGymaaqabaWccaaISaGaamOAamaa
BaaameaacaaIXaaabeaaliaaiYcacaWGPbWaaSbaaWqaaiaaikdaae
qaaSGaaGilaiaadQgadaWgaaadbaGaaGOmaaqabaaaleqaaOGaaiil
aaaa@4358@
dont la contribution à la
covariance susmentionnée est d’ordre
O
i
1
,
j
1
,
i
2
,
j
2
(
β
)
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWGpbWaaS
baaSqaaiaadMgadaWgaaadbaGaaGymaaqabaWccaaISaGaamOAamaa
BaaameaacaaIXaaabeaaliaaiYcacaWGPbWaaSbaaWqaaiaaikdaae
qaaSGaaGilaiaadQgadaWgaaadbaGaaGOmaaqabaaaleqaaOWaaeWa
aeaacqaHYoGyaiaawIcacaGLPaaaaaa@45CF@
pour une suite
β
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacqaHYoGyaa
a@3992@
qui tend vers zéro, apportent à
D
2
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWGebWaaS
baaSqaaiaaikdaaeqaaaaa@39A2@
un terme d’ordre
O
(
λ
β
)
.
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWGpbWaae
WaaeaacqaH7oaBcqaHYoGyaiaawIcacaGLPaaacaGGUaaaaa@3E55@
Or, soit
b
i
,
j
1
,
j
2
:=
c
i
,
j
1
−
1
(
w
j
1
,
j
2
−
w
i
,
j
2
)
,
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWGIbWaaS
baaSqaaiaadMgacaaISaGaamOAamaaBaaameaacaaIXaaabeaaliaa
iYcacaWGQbWaaSbaaWqaaiaaikdaaeqaaaWcbeaakiaaiQdacaaI9a
Gaam4yamaaDaaaleaacaWGPbGaaGilaiaadQgadaWgaaadbaGaaGym
aaqabaaaleaacqGHsislcaaIXaaaaOWaaeWaaeaacaWG3bWaaSbaaS
qaaiaadQgadaWgaaadbaGaaGymaaqabaWccaaISaGaamOAamaaBaaa
meaacaaIYaaabeaaaSqabaGccqGHsislcaWG3bWaaSbaaSqaaiaadM
gacaaISaGaamOAamaaBaaameaacaaIYaaabeaaaSqabaaakiaawIca
caGLPaaacaaISaaaaa@5496@
a
i
,
j
1
,
j
2
:=
t
−
m
i
+
d
i
,
j
1
−
b
i
,
j
1
,
j
2
ε
j
2
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWGHbWaaS
baaSqaaiaadMgacaaISaGaamOAamaaBaaameaacaaIXaaabeaaliaa
iYcacaWGQbWaaSbaaWqaaiaaikdaaeqaaaWcbeaakiaaiQdacaaI9a
GaamiDaiabgkHiTiaad2gadaWgaaWcbaGaamyAaaqabaGccqGHRaWk
caWGKbWaaSbaaSqaaiaadMgacaaISaGaamOAamaaBaaameaacaaIXa
aabeaaaSqabaGccqGHsislcaWGIbWaaSbaaSqaaiaadMgacaaISaGa
amOAamaaBaaameaacaaIXaaabeaaliaaiYcacaWGQbWaaSbaaWqaai
aaikdaaeqaaaWcbeaakiabew7aLnaaBaaaleaacaWGQbWaaSbaaWqa
aiaaikdaaeqaaaWcbeaaaaa@5618@
et notons que
t
−
m
i
+
d
i
,
j
1
=
a
i
,
j
1
,
j
2
+
b
i
,
j
1
,
j
2
ε
j
2
.
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWG0bGaey
OeI0IaamyBamaaBaaaleaacaWGPbaabeaakiabgUcaRiaadsgadaWg
aaWcbaGaamyAaiaaiYcacaWGQbWaaSbaaWqaaiaaigdaaeqaaaWcbe
aakiaai2dacaWGHbWaaSbaaSqaaiaadMgacaaISaGaamOAamaaBaaa
meaacaaIXaaabeaaliaaiYcacaWGQbWaaSbaaWqaaiaaikdaaeqaaa
WcbeaakiabgUcaRiaadkgadaWgaaWcbaGaamyAaiaaiYcacaWGQbWa
aSbaaWqaaiaaigdaaeqaaSGaaGilaiaadQgadaWgaaadbaGaaGOmaa
qabaaaleqaaOGaeqyTdu2aaSbaaSqaaiaadQgadaWgaaadbaGaaGOm
aaqabaaaleqaaOGaaGOlaaaa@560B@
Puisque
a
i
,
j
1
,
j
2
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWGHbWaaS
baaSqaaiaadMgacaaISaGaamOAamaaBaaameaacaaIXaaabeaaliaa
iYcacaWGQbWaaSbaaWqaaiaaikdaaeqaaaWcbeaaaaa@3F22@
ne dépend pas de
ε
j
1
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacqaH1oqzda
WgaaWcbaGaamOAamaaBaaameaacaaIXaaabeaaaSqabaaaaa@3BA6@
ni de
ε
j
2
,
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacqaH1oqzda
WgaaWcbaGaamOAamaaBaaameaacaaIYaaabeaaaSqabaGccaGGSaaa
aa@3C61@
il s’ensuit que
E
(
I
(
ε
j
1
≤
t
−
m
i
1
+
d
i
1
,
j
1
)
I
(
ε
j
2
≤
t
−
m
i
2
+
d
i
2
,
j
2
)
)
=
E
(
E
(
I
(
ε
j
1
≤
a
i
1
,
j
1
,
j
2
+
b
i
1
,
j
1
,
j
2
ε
j
2
)
I
(
ε
j
2
≤
a
i
2
,
j
2
,
j
1
+
b
i
2
,
j
2
,
j
1
ε
j
1
)
|
ε
k
,
k
≠
j
1
,
j
2
)
)
=
E
(
∫
−
∞
ε
i
1
,
i
2
,
j
1
,
j
2
*
G
(
a
i
2
,
j
2
,
j
1
+
b
i
2
,
j
2
,
j
1
ε
|
x
j
2
)
d
G
(
ε
|
x
j
1
)
)
+
E
(
∫
−
∞
ε
i
2
,
i
1
,
j
2
,
j
1
*
G
(
a
i
1
,
j
1
,
j
2
+
b
i
1
,
j
1
,
j
2
ε
|
x
j
1
)
d
G
(
ε
|
x
j
2
)
)
−
E
(
G
(
ε
i
1
,
i
2
,
j
1
,
j
2
*
|
x
j
1
)
G
(
ε
i
2
,
i
1
,
j
2
,
j
1
*
|
x
j
2
)
)
,
(
A
.12
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaafaqaaeqbba
aaaeaacaWGfbWaaeWaaeaacaWGjbWaaeWaaeaacqaH1oqzdaWgaaWc
baGaamOAamaaBaaameaacaaIXaaabeaaaSqabaGccqGHKjYOcaWG0b
GaeyOeI0IaamyBamaaBaaaleaacaWGPbWaaSbaaWqaaiaaigdaaeqa
aaWcbeaakiabgUcaRiaadsgadaWgaaWcbaGaamyAamaaBaaameaaca
aIXaaabeaaliaaiYcacaWGQbWaaSbaaWqaaiaaigdaaeqaaaWcbeaa
aOGaayjkaiaawMcaaiaadMeadaqadaqaaiabew7aLnaaBaaaleaaca
WGQbWaaSbaaWqaaiaaikdaaeqaaaWcbeaakiabgsMiJkaadshacqGH
sislcaWGTbWaaSbaaSqaaiaadMgadaWgaaadbaGaaGOmaaqabaaale
qaaOGaey4kaSIaamizamaaBaaaleaacaWGPbWaaSbaaWqaaiaaikda
aeqaaSGaaGilaiaadQgadaWgaaadbaGaaGOmaaqabaaaleqaaaGcca
GLOaGaayzkaaaacaGLOaGaayzkaaaabaGaaGjbVlaaysW7caaMe8Ua
aGjbVlaaysW7caaMe8UaaGjbVlaaysW7caaMe8UaaGjbVlaai2daca
WGfbWaaeWaaeaacaWGfbWaaeWaaeaacaWGjbWaaeWaaeaacqaH1oqz
daWgaaWcbaGaamOAamaaBaaameaacaaIXaaabeaaaSqabaGccqGHKj
YOcaWGHbWaaSbaaSqaaiaadMgadaWgaaadbaGaaGymaaqabaWccaaI
SaGaamOAamaaBaaameaacaaIXaaabeaaliaaiYcacaWGQbWaaSbaaW
qaaiaaikdaaeqaaaWcbeaakiabgUcaRiaadkgadaWgaaWcbaGaamyA
amaaBaaameaacaaIXaaabeaaliaaiYcacaWGQbWaaSbaaWqaaiaaig
daaeqaaSGaaGilaiaadQgadaWgaaadbaGaaGOmaaqabaaaleqaaOGa
eqyTdu2aaSbaaSqaaiaadQgadaWgaaadbaGaaGOmaaqabaaaleqaaa
GccaGLOaGaayzkaaWaaqGaaeaacaWGjbWaaeWaaeaacqaH1oqzdaWg
aaWcbaGaamOAamaaBaaameaacaaIYaaabeaaaSqabaGccqGHKjYOca
WGHbWaaSbaaSqaaiaadMgadaWgaaadbaGaaGOmaaqabaWccaaISaGa
amOAamaaBaaameaacaaIYaaabeaaliaaiYcacaWGQbWaaSbaaWqaai
aaigdaaeqaaaWcbeaakiabgUcaRiaadkgadaWgaaWcbaGaamyAamaa
BaaameaacaaIYaaabeaaliaaiYcacaWGQbWaaSbaaWqaaiaaikdaae
qaaSGaaGilaiaadQgadaWgaaadbaGaaGymaaqabaaaleqaaOGaeqyT
du2aaSbaaSqaaiaadQgadaWgaaadbaGaaGymaaqabaaaleqaaaGcca
GLOaGaayzkaaGaaGjbVdGaayjcSdGaaGjbVlabew7aLnaaBaaaleaa
caWGRbaabeaakiaaiYcacaWGRbGaeyiyIKRaamOAamaaBaaaleaaca
aIXaaabeaakiaaiYcacaWGQbWaaSbaaSqaaiaaikdaaeqaaaGccaGL
OaGaayzkaaaacaGLOaGaayzkaaaabaGaaGjbVlaaysW7caaMe8UaaG
jbVlaaysW7caaMe8UaaGjbVlaaysW7caaMe8UaaGjbVlaai2dacaWG
fbWaaeWaaeaadaWdXaqabSqaaiabgkHiTiabg6HiLcqaaiabew7aLn
aaDaaabaGaamyAamaaBaaameaacaaIXaaabeaaliaaiYcacaWGPbWa
aSbaaWqaaiaaikdaaeqaaSGaaGilaiaadQgadaWgaaadbaGaaGymaa
qabaWccaaISaGaamOAamaaBaaameaacaaIYaaabeaaaSqaaiaaiQca
aaaaniabgUIiYdGccaWGhbWaaeWaaeaadaabcaqaaiaadggadaWgaa
WcbaGaamyAamaaBaaameaacaaIYaaabeaaliaaiYcacaWGQbWaaSba
aWqaaiaaikdaaeqaaSGaaGilaiaadQgadaWgaaadbaGaaGymaaqaba
aaleqaaOGaey4kaSIaamOyamaaBaaaleaacaWGPbWaaSbaaWqaaiaa
ikdaaeqaaSGaaGilaiaadQgadaWgaaadbaGaaGOmaaqabaWccaaISa
GaamOAamaaBaaameaacaaIXaaabeaaaSqabaGccqaH1oqzcaaMe8oa
caGLiWoacaaMe8UaamiEamaaBaaaleaacaWGQbWaaSbaaWqaaiaaik
daaeqaaaWcbeaaaOGaayjkaiaawMcaaiaadsgacaWGhbWaaeWaaeaa
daabcaqaaiabew7aLjaaysW7aiaawIa7aiaaysW7caWG4bWaaSbaaS
qaaiaadQgadaWgaaadbaGaaGymaaqabaaaleqaaaGccaGLOaGaayzk
aaaacaGLOaGaayzkaaaabaGaaGjbVlaaysW7caaMe8UaaGjbVlaays
W7caaMe8UaaGjbVlaaysW7caaMe8UaaGjbVlaaysW7cqGHRaWkcaWG
fbWaaeWaaeaadaWdXaqabSqaaiabgkHiTiabg6HiLcqaaiabew7aLn
aaDaaabaGaamyAamaaBaaameaacaaIYaaabeaaliaaiYcacaWGPbWa
aSbaaWqaaiaaigdaaeqaaSGaaGilaiaadQgadaWgaaadbaGaaGOmaa
qabaWccaaISaGaamOAamaaBaaameaacaaIXaaabeaaaSqaaiaaiQca
aaaaniabgUIiYdGccaWGhbWaaeWaaeaadaabcaqaaiaadggadaWgaa
WcbaGaamyAamaaBaaameaacaaIXaaabeaaliaaiYcacaWGQbWaaSba
aWqaaiaaigdaaeqaaSGaaGilaiaadQgadaWgaaadbaGaaGOmaaqaba
aaleqaaOGaey4kaSIaamOyamaaBaaaleaacaWGPbWaaSbaaWqaaiaa
igdaaeqaaSGaaGilaiaadQgadaWgaaadbaGaaGymaaqabaWccaaISa
GaamOAamaaBaaameaacaaIYaaabeaaaSqabaGccqaH1oqzcaaMe8oa
caGLiWoacaaMe8UaamiEamaaBaaaleaacaWGQbWaaSbaaWqaaiaaig
daaeqaaaWcbeaaaOGaayjkaiaawMcaaiaadsgacaWGhbWaaeWaaeaa
daabcaqaaiabew7aLjaaysW7aiaawIa7aiaaysW7caWG4bWaaSbaaS
qaaiaadQgadaWgaaadbaGaaGOmaaqabaaaleqaaaGccaGLOaGaayzk
aaaacaGLOaGaayzkaaaabaGaaGjbVlaaysW7caaMe8UaaGjbVlaays
W7caaMe8UaaGjbVlaaysW7caaMe8UaaGjbVlaaysW7cqGHsislcaWG
fbWaaeWaaeaacaWGhbWaaeWaaeaadaabcaqaaiabew7aLnaaDaaale
aacaWGPbWaaSbaaWqaaiaaigdaaeqaaSGaaGilaiaadMgadaWgaaad
baGaaGOmaaqabaWccaaISaGaamOAamaaBaaameaacaaIXaaabeaali
aaiYcacaWGQbWaaSbaaWqaaiaaikdaaeqaaaWcbaGaaGOkaaaakiaa
ysW7aiaawIa7aiaaysW7caWG4bWaaSbaaSqaaiaadQgadaWgaaadba
GaaGymaaqabaaaleqaaaGccaGLOaGaayzkaaGaam4ramaabmaabaWa
aqGaaeaacqaH1oqzdaqhaaWcbaGaamyAamaaBaaameaacaaIYaaabe
aaliaaiYcacaWGPbWaaSbaaWqaaiaaigdaaeqaaSGaaGilaiaadQga
daWgaaadbaGaaGOmaaqabaWccaaISaGaamOAamaaBaaameaacaaIXa
aabeaaaSqaaiaaiQcaaaGccaaMe8oacaGLiWoacaaMe8UaamiEamaa
BaaaleaacaWGQbWaaSbaaWqaaiaaikdaaeqaaaWcbeaaaOGaayjkai
aawMcaaaGaayjkaiaawMcaaiaaiYcaaaGaaGzbVlaacIcacaGGbbGa
aiOlaiaaigdacaaIYaGaaiykaaaa@A1D8@
où
ε
i
1
,
i
2
,
j
1
,
j
2
*
:=
a
i
1,
j
1
,
j
2
+
a
i
2
,
j
2
,
j
1
b
i
1
,
j
1
,
j
2
1
−
b
i
1
,
j
1
,
j
2
b
i
2
,
j
2
,
j
1
.
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacqaH1oqzda
qhaaWcbaGaamyAamaaBaaameaacaaIXaaabeaaliaaiYcacaWGPbWa
aSbaaWqaaiaaikdaaeqaaSGaaGilaiaadQgadaWgaaadbaGaaGymaa
qabaWccaaISaGaamOAamaaBaaameaacaaIYaaabeaaaSqaaiaaiQca
aaGccaaI6aGaaGypamaalaaabaGaamyyamaaBaaaleaacaWGPbWaaS
baaWqaaiaaigdacaaISaaabeaaliaadQgadaWgaaadbaGaaGymaaqa
baWccaaISaGaamOAamaaBaaameaacaaIYaaabeaaaSqabaGccqGHRa
WkcaWGHbWaaSbaaSqaaiaadMgadaWgaaadbaGaaGOmaaqabaWccaaI
SaGaamOAamaaBaaameaacaaIYaaabeaaliaaiYcacaWGQbWaaSbaaW
qaaiaaigdaaeqaaaWcbeaakiaadkgadaWgaaWcbaGaamyAamaaBaaa
meaacaaIXaaabeaaliaaiYcacaWGQbWaaSbaaWqaaiaaigdaaeqaaS
GaaGilaiaadQgadaWgaaadbaGaaGOmaaqabaaaleqaaaGcbaGaaGym
aiabgkHiTiaadkgadaWgaaWcbaGaamyAamaaBaaameaacaaIXaaabe
aaliaaiYcacaWGQbWaaSbaaWqaaiaaigdaaeqaaSGaaGilaiaadQga
daWgaaadbaGaaGOmaaqabaaaleqaaOGaamOyamaaBaaaleaacaWGPb
WaaSbaaWqaaiaaikdaaeqaaSGaaGilaiaadQgadaWgaaadbaGaaGOm
aaqabaWccaaISaGaamOAamaaBaaameaacaaIXaaabeaaaSqabaaaaO
GaaGOlaaaa@71F4@
Notons que les deux espérances aux troisième et
quatrième lignes de (A.12) sont les mêmes si
i
1
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWGPbWaaS
baaSqaaiaaigdaaeqaaaaa@39C6@
et
j
1
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWGQbWaaS
baaSqaaiaaigdaaeqaaaaa@39C7@
sont remplacés par
i
2
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWGPbWaaS
baaSqaaiaaikdaaeqaaaaa@39C7@
et
j
2
,
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWGQbWaaS
baaSqaaiaaikdaaeqaaOGaaiilaaaa@3A82@
respectivement. Donc, il suffit
d’analyser la première espérance. Étant donné que
ε
i
1
,
i
2
,
j
1
,
j
2
*
=
t
−
m
i
1
+
d
i
1
,
j
1
+
b
i
1
,
j
1
,
j
2
(
t
−
m
i
2
−
ε
j
2
)
+
R
(
ε
i
1
,
i
2
,
j
1
,
j
2
*
)
,
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacqaH1oqzda
qhaaWcbaGaamyAamaaBaaameaacaaIXaaabeaaliaaiYcacaWGPbWa
aSbaaWqaaiaaikdaaeqaaSGaaGilaiaadQgadaWgaaadbaGaaGymaa
qabaWccaaISaGaamOAamaaBaaameaacaaIYaaabeaaaSqaaiaaiQca
aaGccaaI9aGaamiDaiabgkHiTiaad2gadaWgaaWcbaGaamyAamaaBa
aameaacaaIXaaabeaaaSqabaGccqGHRaWkcaWGKbWaaSbaaSqaaiaa
dMgadaWgaaadbaGaaGymaaqabaWccaaISaGaamOAamaaBaaameaaca
aIXaaabeaaaSqabaGccqGHRaWkcaWGIbWaaSbaaSqaaiaadMgadaWg
aaadbaGaaGymaaqabaWccaaISaGaamOAamaaBaaameaacaaIXaaabe
aaliaaiYcacaWGQbWaaSbaaWqaaiaaikdaaeqaaaWcbeaakmaabmaa
baGaamiDaiabgkHiTiaad2gadaWgaaWcbaGaamyAamaaBaaameaaca
aIYaaabeaaaSqabaGccqGHsislcqaH1oqzdaWgaaWcbaGaamOAamaa
BaaameaacaaIYaaabeaaaSqabaaakiaawIcacaGLPaaacqGHRaWkca
WGsbWaaeWaaeaacqaH1oqzdaqhaaWcbaGaamyAamaaBaaameaacaaI
XaaabeaaliaaiYcacaWGPbWaaSbaaWqaaiaaikdaaeqaaSGaaGilai
aadQgadaWgaaadbaGaaGymaaqabaWccaaISaGaamOAamaaBaaameaa
caaIYaaabeaaaSqaaiaaiQcaaaaakiaawIcacaGLPaaacaaISaaaaa@74C7@
où
E
1
/
4
(
|
R
(
ε
i
1
,
i
2
,
j
1
,
j
2
*
)
|
4
)
=
O
i
1
,
i
2
,
j
1
,
j
2
(
λ
n
−
1
+
(
n
λ
)
−
3
/
2
)
,
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWGfbWaaW
baaSqabeaadaWcgaqaaiaaigdaaeaacaaI0aaaaaaakmaabmaabaWa
aqWaaeaacaWGsbWaaeWaaeaacqaH1oqzdaqhaaWcbaGaamyAamaaBa
aameaacaaIXaaabeaaliaaiYcacaWGPbWaaSbaaWqaaiaaikdaaeqa
aSGaaGilaiaadQgadaWgaaadbaGaaGymaaqabaWccaaISaGaamOAam
aaBaaameaacaaIYaaabeaaaSqaaiaaiQcaaaaakiaawIcacaGLPaaa
caaMc8oacaGLhWUaayjcSdWaaWbaaSqabeaacaaMc8UaaGinaaaaaO
GaayjkaiaawMcaaiaai2dacaWGpbWaaSbaaSqaaiaadMgadaWgaaad
baGaaGymaaqabaWccaaISaGaamyAamaaBaaameaacaaIYaaabeaali
aaiYcacaWGQbWaaSbaaWqaaiaaigdaaeqaaSGaaGilaiaadQgadaWg
aaadbaGaaGOmaaqabaaaleqaaOWaaeWaaeaacqaH7oaBcaWGUbWaaW
baaSqabeaacqGHsislcaaIXaaaaOGaey4kaSYaaeWaaeaacaWGUbGa
eq4UdWgacaGLOaGaayzkaaWaaWbaaSqabeaacqGHsisldaWcgaqaai
aaiodaaeaacaaIYaaaaaaaaOGaayjkaiaawMcaaiaaiYcaaaa@6BD7@
on voit que
E
(
∫
−
∞
ε
i
1
,
i
2
,
j
1
,
j
2
*
G
(
a
i
2
,
j
2
,
j
1
+
b
i
2
,
j
2
,
j
1
ε
|
x
j
2
)
d
G
(
ε
|
x
j
1
)
)
=
G
(
t
−
m
i
1
|
x
j
1
)
G
(
t
−
m
i
2
|
x
j
2
)
+
G
(
1
,
0
)
(
t
−
m
i
1
|
x
j
1
)
G
(
t
−
m
i
2
|
x
j
2
)
[
E
(
d
i
1
,
j
1
)
+
b
i
1
,
j
1
,
j
2
(
t
−
m
i
2
)
]
+
G
(
1
,
0
)
(
t
−
m
i
2
|
x
j
2
)
G
(
t
−
m
i
1
|
x
j
1
)
E
(
d
i
2
,
j
2
)
+
G
(
1
,
0
)
(
t
−
m
i
2
|
x
j
2
)
b
i
2
,
j
2
,
j
1
∫
−
∞
t
−
m
i
1
ε
d
G
(
ε
|
x
j
1
)
+
1
2
G
(
2
,
0
)
(
t
−
m
i
1
|
x
j
1
)
G
(
t
−
m
i
2
|
x
j
2
)
E
(
d
i
1
,
j
1
2
)
+
1
2
G
(
2
,
0
)
(
t
−
m
i
2
|
x
j
2
)
G
(
t
−
m
i
1
|
x
j
1
)
E
(
d
i
2
,
j
2
2
)
+
G
(
1
,
0
)
(
t
−
m
i
1
|
x
j
1
)
G
(
1
,
0
)
(
t
−
m
i
2
|
x
j
2
)
E
(
d
i
1
,
j
1
d
i
2
,
j
2
)
+
o
i
1
,
i
2
,
j
1
,
j
2
(
λ
4
+
(
n
λ
)
−
1
)
,
(
A
.13
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrVipeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaafaqaaeWbba
aaaeaacaWGfbWaaeWaaeaadaWdXaqabSqaaiabgkHiTiabg6HiLcqa
aiabew7aLnaaDaaabaGaamyAamaaBaaameaacaaIXaaabeaaliaaiY
cacaWGPbWaaSbaaWqaaiaaikdaaeqaaSGaaGilaiaadQgadaWgaaad
baGaaGymaaqabaWccaaISaGaamOAamaaBaaameaacaaIYaaabeaaaS
qaaiaaiQcaaaaaniabgUIiYdGccaWGhbWaaeWaaeaadaabcaqaaiaa
dggadaWgaaWcbaGaamyAamaaBaaameaacaaIYaaabeaaliaaiYcaca
WGQbWaaSbaaWqaaiaaikdaaeqaaSGaaGilaiaadQgadaWgaaadbaGa
aGymaaqabaaaleqaaOGaey4kaSIaamOyamaaBaaaleaacaWGPbWaaS
baaWqaaiaaikdaaeqaaSGaaGilaiaadQgadaWgaaadbaGaaGOmaaqa
baWccaaISaGaamOAamaaBaaameaacaaIXaaabeaaaSqabaGccqaH1o
qzcaaMc8oacaGLiWoacaaMc8UaamiEamaaBaaaleaacaWGQbWaaSba
aWqaaiaaikdaaeqaaaWcbeaaaOGaayjkaiaawMcaaiaadsgacaWGhb
WaaeWaaeaadaabcaqaaiabew7aLjaaykW7aiaawIa7aiaaykW7caWG
4bWaaSbaaSqaaiaadQgadaWgaaadbaGaaGymaaqabaaaleqaaaGcca
GLOaGaayzkaaaacaGLOaGaayzkaaaabaGaaGjbVlaaysW7caaMe8Ua
aGjbVlaaysW7caaI9aGaam4ramaabmaabaWaaqGaaeaacaWG0bGaey
OeI0IaamyBamaaBaaaleaacaWGPbWaaSbaaWqaaiaaigdaaeqaaaWc
beaakiaaykW7aiaawIa7aiaaykW7caWG4bWaaSbaaSqaaiaadQgada
WgaaadbaGaaGymaaqabaaaleqaaaGccaGLOaGaayzkaaGaam4ramaa
bmaabaWaaqGaaeaacaWG0bGaeyOeI0IaamyBamaaBaaaleaacaWGPb
WaaSbaaWqaaiaaikdaaeqaaaWcbeaakiaaykW7aiaawIa7aiaaykW7
caWG4bWaaSbaaSqaaiaadQgadaWgaaadbaGaaGOmaaqabaaaleqaaa
GccaGLOaGaayzkaaaabaGaaGjbVlaaysW7caaMe8UaaGjbVlaaysW7
caaMe8UaaGjbVlabgUcaRiaadEeadaahaaWcbeqaamaabmaabaGaaG
ymaiaacYcacaaIWaaacaGLOaGaayzkaaaaaOWaaeWaaeaadaabcaqa
aiaadshacqGHsislcaWGTbWaaSbaaSqaaiaadMgadaWgaaadbaGaaG
ymaaqabaaaleqaaOGaaGPaVdGaayjcSdGaaGPaVlaadIhadaWgaaWc
baGaamOAamaaBaaameaacaaIXaaabeaaaSqabaaakiaawIcacaGLPa
aacaWGhbWaaeWaaeaadaabcaqaaiaadshacqGHsislcaWGTbWaaSba
aSqaaiaadMgadaWgaaadbaGaaGOmaaqabaaaleqaaOGaaGPaVdGaay
jcSdGaaGPaVlaadIhadaWgaaWcbaGaamOAamaaBaaameaacaaIYaaa
beaaaSqabaaakiaawIcacaGLPaaadaWadaqaaiaadweadaqadaqaai
aadsgadaWgaaWcbaGaamyAamaaBaaameaacaaIXaaabeaaliaaiYca
caWGQbWaaSbaaWqaaiaaigdaaeqaaaWcbeaaaOGaayjkaiaawMcaai
abgUcaRiaadkgadaWgaaWcbaGaamyAamaaBaaameaacaaIXaaabeaa
liaaiYcacaWGQbWaaSbaaWqaaiaaigdaaeqaaSGaaGilaiaadQgada
WgaaadbaGaaGOmaaqabaaaleqaaOWaaeWaaeaacaWG0bGaeyOeI0Ia
amyBamaaBaaaleaacaWGPbWaaSbaaWqaaiaaikdaaeqaaaWcbeaaaO
GaayjkaiaawMcaaaGaay5waiaaw2faaaqaaiaaysW7caaMe8UaaGjb
VlaaysW7caaMe8UaaGjbVlaaysW7cqGHRaWkcaWGhbWaaWbaaSqabe
aadaqadaqaaiaaigdacaGGSaGaaGimaaGaayjkaiaawMcaaaaakmaa
bmaabaWaaqGaaeaacaWG0bGaeyOeI0IaamyBamaaBaaaleaacaWGPb
WaaSbaaWqaaiaaikdaaeqaaaWcbeaakiaaykW7aiaawIa7aiaaykW7
caWG4bWaaSbaaSqaaiaadQgadaWgaaadbaGaaGOmaaqabaaaleqaaa
GccaGLOaGaayzkaaGaam4ramaabmaabaWaaqGaaeaacaWG0bGaeyOe
I0IaamyBamaaBaaaleaacaWGPbWaaSbaaWqaaiaaigdaaeqaaaWcbe
aakiaaykW7aiaawIa7aiaaykW7caWG4bWaaSbaaSqaaiaadQgadaWg
aaadbaGaaGymaaqabaaaleqaaaGccaGLOaGaayzkaaGaamyramaabm
aabaGaamizamaaBaaaleaacaWGPbWaaSbaaWqaaiaaikdaaeqaaSGa
aGilaiaadQgadaWgaaadbaGaaGOmaaqabaaaleqaaaGccaGLOaGaay
zkaaGaey4kaSIaam4ramaaCaaaleqabaWaaeWaaeaacaaIXaGaaiil
aiaaicdaaiaawIcacaGLPaaaaaGcdaqadaqaamaaeiaabaGaamiDai
abgkHiTiaad2gadaWgaaWcbaGaamyAamaaBaaameaacaaIYaaabeaa
aSqabaGccaaMc8oacaGLiWoacaaMc8UaamiEamaaBaaaleaacaWGQb
WaaSbaaWqaaiaaikdaaeqaaaWcbeaaaOGaayjkaiaawMcaaiaadkga
daWgaaWcbaGaamyAamaaBaaameaacaaIYaaabeaaliaaiYcacaWGQb
WaaSbaaWqaaiaaikdaaeqaaSGaaGilaiaadQgadaWgaaadbaGaaGym
aaqabaaaleqaaOWaa8qmaeqaleaacqGHsislcqGHEisPaeaacaWG0b
GaeyOeI0IaamyBamaaBaaameaacaWGPbWaaSbaaeaacaaIXaaabeaa
aeqaaaqdcqGHRiI8aOGaeqyTduMaamizaiaadEeadaqadaqaamaaei
aabaGaeqyTduMaaGPaVdGaayjcSdGaaGPaVlaadIhadaWgaaWcbaGa
amOAamaaBaaameaacaaIXaaabeaaaSqabaaakiaawIcacaGLPaaaae
aacaaMe8UaaGjbVlaaysW7caaMe8UaaGjbVlaaysW7caaMe8Uaey4k
aSYaaSaaaeaacaaIXaaabaGaaGOmaaaacaWGhbWaaWbaaSqabeaada
qadaqaaiaaikdacaGGSaGaaGimaaGaayjkaiaawMcaaaaakmaabmaa
baWaaqGaaeaacaWG0bGaeyOeI0IaamyBamaaBaaaleaacaWGPbWaaS
baaWqaaiaaigdaaeqaaaWcbeaakiaaykW7aiaawIa7aiaaykW7caWG
4bWaaSbaaSqaaiaadQgadaWgaaadbaGaaGymaaqabaaaleqaaaGcca
GLOaGaayzkaaGaam4ramaabmaabaWaaqGaaeaacaWG0bGaeyOeI0Ia
amyBamaaBaaaleaacaWGPbWaaSbaaWqaaiaaikdaaeqaaaWcbeaaki
aaykW7aiaawIa7aiaaykW7caWG4bWaaSbaaSqaaiaadQgadaWgaaad
baGaaGOmaaqabaaaleqaaaGccaGLOaGaayzkaaGaamyramaabmaaba
GaamizamaaDaaaleaacaWGPbWaaSbaaWqaaiaaigdaaeqaaSGaaGil
aiaadQgadaWgaaadbaGaaGymaaqabaaaleaacaaIYaaaaaGccaGLOa
GaayzkaaGaey4kaSYaaSaaaeaacaaIXaaabaGaaGOmaaaacaWGhbWa
aWbaaSqabeaadaqadaqaaiaaikdacaGGSaGaaGimaaGaayjkaiaawM
caaaaakmaabmaabaWaaqGaaeaacaWG0bGaeyOeI0IaamyBamaaBaaa
leaacaWGPbWaaSbaaWqaaiaaikdaaeqaaaWcbeaakiaaykW7aiaawI
a7aiaaykW7caWG4bWaaSbaaSqaaiaadQgadaWgaaadbaGaaGOmaaqa
baaaleqaaaGccaGLOaGaayzkaaGaam4ramaabmaabaWaaqGaaeaaca
WG0bGaeyOeI0IaamyBamaaBaaaleaacaWGPbWaaSbaaWqaaiaaigda
aeqaaaWcbeaakiaaykW7aiaawIa7aiaaykW7caWG4bWaaSbaaSqaai
aadQgadaWgaaadbaGaaGymaaqabaaaleqaaaGccaGLOaGaayzkaaGa
amyramaabmaabaGaamizamaaDaaaleaacaWGPbWaaSbaaWqaaiaaik
daaeqaaSGaaGilaiaadQgadaWgaaadbaGaaGOmaaqabaaaleaacaaI
YaaaaaGccaGLOaGaayzkaaaabaGaaGjbVlaaysW7caaMe8UaaGjbVl
aaysW7caaMe8UaaGjbVlabgUcaRiaadEeadaahaaWcbeqaamaabmaa
baGaaGymaiaacYcacaaIWaaacaGLOaGaayzkaaaaaOWaaeWaaeaada
abcaqaaiaadshacqGHsislcaWGTbWaaSbaaSqaaiaadMgadaWgaaad
baGaaGymaaqabaaaleqaaOGaaGPaVdGaayjcSdGaaGPaVlaadIhada
WgaaWcbaGaamOAamaaBaaameaacaaIXaaabeaaaSqabaaakiaawIca
caGLPaaacaWGhbWaaWbaaSqabeaadaqadaqaaiaaigdacaGGSaGaaG
imaaGaayjkaiaawMcaaaaakmaabmaabaWaaqGaaeaacaWG0bGaeyOe
I0IaamyBamaaBaaaleaacaWGPbWaaSbaaWqaaiaaikdaaeqaaaWcbe
aakiaaykW7aiaawIa7aiaaykW7caWG4bWaaSbaaSqaaiaadQgadaWg
aaadbaGaaGOmaaqabaaaleqaaaGccaGLOaGaayzkaaGaamyramaabm
aabaGaamizamaaBaaaleaacaWGPbWaaSbaaWqaaiaaigdaaeqaaSGa
aGilaiaadQgadaWgaaadbaGaaGymaaqabaaaleqaaOGaamizamaaBa
aaleaacaWGPbWaaSbaaWqaaiaaikdaaeqaaSGaaGilaiaadQgadaWg
aaadbaGaaGOmaaqabaaaleqaaaGccaGLOaGaayzkaaaabaGaaGjbVl
aaysW7caaMe8UaaGjbVlaaysW7caaMe8UaaGjbVlabgUcaRiaad+ga
daWgaaWcbaGaamyAamaaBaaameaacaaIXaaabeaaliaaiYcacaWGPb
WaaSbaaWqaaiaaikdaaeqaaSGaaGilaiaadQgadaWgaaadbaGaaGym
aaqabaWccaaISaGaamOAamaaBaaameaacaaIYaaabeaaaSqabaGcda
qadaqaaiabeU7aSnaaCaaaleqabaGaaGinaaaakiabgUcaRmaabmaa
baGaamOBaiabeU7aSbGaayjkaiaawMcaamaaCaaaleqabaGaeyOeI0
IaaGymaaaaaOGaayjkaiaawMcaaiaaiYcaaaGaaGzbVlaacIcacaGG
bbGaaiOlaiaaigdacaaIZaGaaiykaaaa@17EC@
et que
E
(
G
(
ε
i
1
,
i
2
,
j
1
,
j
2
*
|
x
j
1
)
G
(
ε
i
2
,
i
1
,
j
2
,
j
1
*
|
x
j
2
)
)
=
G
(
t
−
m
i
1
|
x
j
1
)
G
(
t
−
m
i
2
|
x
j
2
)
+
G
(
1
,
0
)
(
t
−
m
i
1
|
x
j
1
)
G
(
t
−
m
i
2
|
x
j
2
)
[
E
(
d
i
1
,
j
1
)
+
b
i
1
,
j
1
,
j
2
(
t
−
m
i
2
)
]
+
G
(
1
,
0
)
(
t
−
m
i
2
|
x
j
2
)
G
(
t
−
m
i
1
|
x
j
1
)
[
E
(
d
i
2
,
j
2
)
+
b
i
2
,
j
2
,
j
1
(
t
−
m
i
1
)
]
+
1
2
G
(
2
,
0
)
(
t
−
m
i
1
|
x
j
1
)
G
(
t
−
m
i
2
|
x
j
2
)
E
(
d
i
1
,
j
1
2
)
+
1
2
G
(
2
,
0
)
(
t
−
m
i
2
|
x
j
2
)
G
(
t
−
m
i
1
|
x
j
1
)
E
(
d
i
2
,
j
2
2
)
+
G
(
1
,
0
)
(
t
−
m
i
1
|
x
j
1
)
G
(
1
,
0
)
(
t
−
m
i
2
|
x
j
2
)
E
(
d
i
1
,
j
1
d
i
2
,
j
2
)
+
o
i
1
,
i
2
,
j
1
,
j
2
(
λ
4
+
(
n
λ
)
−
1
)
.
(
A
.14
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrViFfea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaafaqaaeacba
aaaaqaaiaadweadaqadaqaaiaadEeadaqadaqaamaaeiaabaGaeqyT
du2aa0baaSqaaiaadMgadaWgaaadbaGaaGymaaqabaWccaaISaGaam
yAamaaBaaameaacaaIYaaabeaaliaaiYcacaWGQbWaaSbaaWqaaiaa
igdaaeqaaSGaaGilaiaadQgadaWgaaadbaGaaGOmaaqabaaaleaaca
aIQaaaaOGaaGPaVdGaayjcSdGaaGPaVlaadIhadaWgaaWcbaGaamOA
amaaBaaameaacaaIXaaabeaaaSqabaaakiaawIcacaGLPaaacaWGhb
WaaeWaaeaadaabcaqaaiabew7aLnaaDaaaleaacaWGPbWaaSbaaWqa
aiaaikdaaeqaaSGaaGilaiaadMgadaWgaaadbaGaaGymaaqabaWcca
aISaGaamOAamaaBaaameaacaaIYaaabeaaliaaiYcacaWGQbWaaSba
aWqaaiaaigdaaeqaaaWcbaGaaGOkaaaakiaaykW7aiaawIa7aiaayk
W7caWG4bWaaSbaaSqaaiaadQgadaWgaaadbaGaaGOmaaqabaaaleqa
aaGccaGLOaGaayzkaaaacaGLOaGaayzkaaaabaGaaGjbVlaaysW7ca
aMe8UaaGjbVlaaysW7caaI9aGaam4ramaabmaabaWaaqGaaeaacaWG
0bGaeyOeI0IaamyBamaaBaaaleaacaWGPbWaaSbaaWqaaiaaigdaae
qaaaWcbeaakiaaykW7aiaawIa7aiaaykW7caWG4bWaaSbaaSqaaiaa
dQgadaWgaaadbaGaaGymaaqabaaaleqaaaGccaGLOaGaayzkaaGaam
4ramaabmaabaWaaqGaaeaacaWG0bGaeyOeI0IaamyBamaaBaaaleaa
caWGPbWaaSbaaWqaaiaaikdaaeqaaaWcbeaakiaaykW7aiaawIa7ai
aaykW7caWG4bWaaSbaaSqaaiaadQgadaWgaaadbaGaaGOmaaqabaaa
leqaaaGccaGLOaGaayzkaaaabaGaaGjbVlaaysW7caaMe8UaaGjbVl
aaysW7caaMe8UaaGjbVlabgUcaRiaadEeadaahaaWcbeqaamaabmaa
baGaaGymaiaacYcacaaIWaaacaGLOaGaayzkaaaaaOWaaeWaaeaada
abcaqaaiaadshacqGHsislcaWGTbWaaSbaaSqaaiaadMgadaWgaaad
baGaaGymaaqabaaaleqaaOGaaGPaVdGaayjcSdGaaGPaVlaadIhada
WgaaWcbaGaamOAamaaBaaameaacaaIXaaabeaaaSqabaaakiaawIca
caGLPaaacaWGhbWaaeWaaeaadaabcaqaaiaadshacqGHsislcaWGTb
WaaSbaaSqaaiaadMgadaWgaaadbaGaaGOmaaqabaaaleqaaOGaaGPa
VdGaayjcSdGaaGPaVlaadIhadaWgaaWcbaGaamOAamaaBaaameaaca
aIYaaabeaaaSqabaaakiaawIcacaGLPaaadaWadaqaaiaadweadaqa
daqaaiaadsgadaWgaaWcbaGaamyAamaaBaaameaacaaIXaaabeaali
aaiYcacaWGQbWaaSbaaWqaaiaaigdaaeqaaaWcbeaaaOGaayjkaiaa
wMcaaiabgUcaRiaadkgadaWgaaWcbaGaamyAamaaBaaameaacaaIXa
aabeaaliaaiYcacaWGQbWaaSbaaWqaaiaaigdaaeqaaSGaaGilaiaa
dQgadaWgaaadbaGaaGOmaaqabaaaleqaaOWaaeWaaeaacaWG0bGaey
OeI0IaamyBamaaBaaaleaacaWGPbWaaSbaaWqaaiaaikdaaeqaaaWc
beaaaOGaayjkaiaawMcaaaGaay5waiaaw2faaaqaaiaaysW7caaMe8
UaaGjbVlaaysW7caaMe8UaaGjbVlaaysW7cqGHRaWkcaWGhbWaaWba
aSqabeaadaqadaqaaiaaigdacaGGSaGaaGimaaGaayjkaiaawMcaaa
aakmaabmaabaWaaqGaaeaacaWG0bGaeyOeI0IaamyBamaaBaaaleaa
caWGPbWaaSbaaWqaaiaaikdaaeqaaaWcbeaakiaaykW7aiaawIa7ai
aaykW7caWG4bWaaSbaaSqaaiaadQgadaWgaaadbaGaaGOmaaqabaaa
leqaaaGccaGLOaGaayzkaaGaam4ramaabmaabaWaaqGaaeaacaWG0b
GaeyOeI0IaamyBamaaBaaaleaacaWGPbWaaSbaaWqaaiaaigdaaeqa
aaWcbeaakiaaykW7aiaawIa7aiaaykW7caWG4bWaaSbaaSqaaiaadQ
gadaWgaaadbaGaaGymaaqabaaaleqaaaGccaGLOaGaayzkaaWaamWa
aeaacaWGfbWaaeWaaeaacaWGKbWaaSbaaSqaaiaadMgadaWgaaadba
GaaGOmaaqabaWccaaISaGaamOAamaaBaaameaacaaIYaaabeaaaSqa
baaakiaawIcacaGLPaaacqGHRaWkcaWGIbWaaSbaaSqaaiaadMgada
WgaaadbaGaaGOmaaqabaWccaaISaGaamOAamaaBaaameaacaaIYaaa
beaaliaaiYcacaWGQbWaaSbaaWqaaiaaigdaaeqaaaWcbeaakmaabm
aabaGaamiDaiabgkHiTiaad2gadaWgaaWcbaGaamyAamaaBaaameaa
caaIXaaabeaaaSqabaaakiaawIcacaGLPaaaaiaawUfacaGLDbaaae
aacaaMe8UaaGjbVlaaysW7caaMe8UaaGjbVlaaysW7caaMe8Uaey4k
aSYaaSaaaeaacaaIXaaabaGaaGOmaaaacaWGhbWaaWbaaSqabeaada
qadaqaaiaaikdacaGGSaGaaGimaaGaayjkaiaawMcaaaaakmaabmaa
baWaaqGaaeaacaWG0bGaeyOeI0IaamyBamaaBaaaleaacaWGPbWaaS
baaWqaaiaaigdaaeqaaaWcbeaakiaaykW7aiaawIa7aiaaykW7caWG
4bWaaSbaaSqaaiaadQgadaWgaaadbaGaaGymaaqabaaaleqaaaGcca
GLOaGaayzkaaGaam4ramaabmaabaWaaqGaaeaacaWG0bGaeyOeI0Ia
amyBamaaBaaaleaacaWGPbWaaSbaaWqaaiaaikdaaeqaaaWcbeaaki
aaykW7aiaawIa7aiaaykW7caWG4bWaaSbaaSqaaiaadQgadaWgaaad
baGaaGOmaaqabaaaleqaaaGccaGLOaGaayzkaaGaamyramaabmaaba
GaamizamaaDaaaleaacaWGPbWaaSbaaWqaaiaaigdaaeqaaSGaaGil
aiaadQgadaWgaaadbaGaaGymaaqabaaaleaacaaIYaaaaaGccaGLOa
GaayzkaaaabaGaaGjbVlaaysW7caaMe8UaaGjbVlaaysW7caaMe8Ua
aGjbVlabgUcaRmaalaaabaGaaGymaaqaaiaaikdaaaGaam4ramaaCa
aaleqabaWaaeWaaeaacaaIYaGaaiilaiaaicdaaiaawIcacaGLPaaa
aaGcdaqadaqaamaaeiaabaGaamiDaiabgkHiTiaad2gadaWgaaWcba
GaamyAamaaBaaameaacaaIYaaabeaaaSqabaGccaaMc8oacaGLiWoa
caaMc8UaamiEamaaBaaaleaacaWGQbWaaSbaaWqaaiaaikdaaeqaaa
WcbeaaaOGaayjkaiaawMcaaiaadEeadaqadaqaamaaeiaabaGaamiD
aiabgkHiTiaad2gadaWgaaWcbaGaamyAamaaBaaameaacaaIXaaabe
aaaSqabaGccaaMc8oacaGLiWoacaaMc8UaamiEamaaBaaaleaacaWG
QbWaaSbaaWqaaiaaigdaaeqaaaWcbeaaaOGaayjkaiaawMcaaiaadw
eadaqadaqaaiaadsgadaqhaaWcbaGaamyAamaaBaaameaacaaIYaaa
beaaliaaiYcacaWGQbWaaSbaaWqaaiaaikdaaeqaaaWcbaGaaGOmaa
aaaOGaayjkaiaawMcaaaqaaiaaysW7caaMe8UaaGjbVlaaysW7caaM
e8UaaGjbVlaaysW7cqGHRaWkcaWGhbWaaWbaaSqabeaadaqadaqaai
aaigdacaGGSaGaaGimaaGaayjkaiaawMcaaaaakmaabmaabaWaaqGa
aeaacaWG0bGaeyOeI0IaamyBamaaBaaaleaacaWGPbWaaSbaaWqaai
aaigdaaeqaaaWcbeaakiaaykW7aiaawIa7aiaaykW7caWG4bWaaSba
aSqaaiaadQgadaWgaaadbaGaaGymaaqabaaaleqaaaGccaGLOaGaay
zkaaGaam4ramaaCaaaleqabaWaaeWaaeaacaaIXaGaaiilaiaaicda
aiaawIcacaGLPaaaaaGcdaqadaqaamaaeiaabaGaamiDaiabgkHiTi
aad2gadaWgaaWcbaGaamyAamaaBaaameaacaaIYaaabeaaaSqabaGc
caaMc8oacaGLiWoacaaMc8UaamiEamaaBaaaleaacaWGQbWaaSbaaW
qaaiaaikdaaeqaaaWcbeaaaOGaayjkaiaawMcaaiaadweadaqadaqa
aiaadsgadaWgaaWcbaGaamyAamaaBaaameaacaaIXaaabeaaliaaiY
cacaWGQbWaaSbaaWqaaiaaigdaaeqaaaWcbeaakiaadsgadaWgaaWc
baGaamyAamaaBaaameaacaaIYaaabeaaliaaiYcacaWGQbWaaSbaaW
qaaiaaikdaaeqaaaWcbeaaaOGaayjkaiaawMcaaaqaaiaaysW7caaM
e8UaaGjbVlaaysW7caaMe8UaaGjbVlaaysW7cqGHRaWkcaWGVbWaaS
baaSqaaiaadMgadaWgaaadbaGaaGymaaqabaWccaaISaGaamyAamaa
BaaameaacaaIYaaabeaaliaaiYcacaWGQbWaaSbaaWqaaiaaigdaae
qaaSGaaGilaiaadQgadaWgaaadbaGaaGOmaaqabaaaleqaaOWaaeWa
aeaacqaH7oaBdaahaaWcbeqaaiaaisdaaaGccqGHRaWkdaqadaqaai
aad6gacqaH7oaBaiaawIcacaGLPaaadaahaaWcbeqaaiabgkHiTiaa
igdaaaaakiaawIcacaGLPaaacaaIUaaaaiaaywW7caaMf8Uaaiikai
aacgeacaGGUaGaaGymaiaaisdacaGGPaaaaa@F4C1@
En utilisant les développements
asymptotiques en (A.4), (A.13) et (A.14), on obtient
cov
(
I
(
ε
j
1
≤
t
−
m
i
1
+
d
i
1
,
j
1
)
,
I
(
ε
j
2
≤
t
−
m
i
2
+
d
i
2
,
j
2
)
)
=
G
(
1
,
0
)
(
t
−
m
i
2
|
x
j
2
)
b
i
2
,
j
2
,
j
1
γ
i
1
,
j
1
+
G
(
1
,
0
)
(
t
−
m
i
1
|
x
j
1
)
b
i
1
,
j
1
,
j
2
γ
i
2
,
j
2
+
G
(
1
,
0
)
(
t
−
m
i
1
|
x
j
1
)
G
(
1
,
0
)
(
t
−
m
i
2
|
x
j
2
)
cov
(
d
i
1
,
j
1
,
d
i
2
,
j
2
)
+
o
i
1
,
i
2
,
j
1
,
j
2
(
λ
4
+
(
n
λ
)
−
1
)
,
(
A
.15
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrVjFfea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaafaqaaeabba
aaaeaacaqGJbGaae4BaiaabAhadaqadaqaaiaadMeadaqadaqaaiab
ew7aLnaaBaaaleaacaWGQbWaaSbaaWqaaiaaigdaaeqaaaWcbeaaki
abgsMiJkaadshacqGHsislcaWGTbWaaSbaaSqaaiaadMgadaWgaaad
baGaaGymaaqabaaaleqaaOGaey4kaSIaamizamaaBaaaleaacaWGPb
WaaSbaaWqaaiaaigdaaeqaaSGaaGilaiaadQgadaWgaaadbaGaaGym
aaqabaaaleqaaaGccaGLOaGaayzkaaGaaGilaiaadMeadaqadaqaai
abew7aLnaaBaaaleaacaWGQbWaaSbaaWqaaiaaikdaaeqaaaWcbeaa
kiabgsMiJkaadshacqGHsislcaWGTbWaaSbaaSqaaiaadMgadaWgaa
adbaGaaGOmaaqabaaaleqaaOGaey4kaSIaamizamaaBaaaleaacaWG
PbWaaSbaaWqaaiaaikdaaeqaaSGaaGilaiaadQgadaWgaaadbaGaaG
OmaaqabaaaleqaaaGccaGLOaGaayzkaaaacaGLOaGaayzkaaaabaGa
aGjbVlaaysW7caaMe8UaaGjbVlaaysW7caaI9aGaam4ramaaCaaale
qabaWaaeWaaeaacaaIXaGaaiilaiaaicdaaiaawIcacaGLPaaaaaGc
daqadaqaamaaeiaabaGaamiDaiabgkHiTiaad2gadaWgaaWcbaGaam
yAamaaBaaameaacaaIYaaabeaaaSqabaGccaaMc8oacaGLiWoacaaM
c8UaamiEamaaBaaaleaacaWGQbWaaSbaaWqaaiaaikdaaeqaaaWcbe
aaaOGaayjkaiaawMcaaiaadkgadaWgaaWcbaGaamyAamaaBaaameaa
caaIYaaabeaaliaaiYcacaWGQbWaaSbaaWqaaiaaikdaaeqaaSGaaG
ilaiaadQgadaWgaaadbaGaaGymaaqabaaaleqaaOGaeq4SdC2aaSba
aSqaaiaadMgadaWgaaadbaGaaGymaaqabaWccaaISaGaamOAamaaBa
aameaacaaIXaaabeaaaSqabaGccqGHRaWkcaWGhbWaaWbaaSqabeaa
daqadaqaaiaaigdacaGGSaGaaGimaaGaayjkaiaawMcaaaaakmaabm
aabaWaaqGaaeaacaWG0bGaeyOeI0IaamyBamaaBaaaleaacaWGPbWa
aSbaaWqaaiaaigdaaeqaaaWcbeaakiaaykW7aiaawIa7aiaaykW7ca
WG4bWaaSbaaSqaaiaadQgadaWgaaadbaGaaGymaaqabaaaleqaaaGc
caGLOaGaayzkaaGaamOyamaaBaaaleaacaWGPbWaaSbaaWqaaiaaig
daaeqaaSGaaGilaiaadQgadaWgaaadbaGaaGymaaqabaWccaaISaGa
amOAamaaBaaameaacaaIYaaabeaaaSqabaGccqaHZoWzdaWgaaWcba
GaamyAamaaBaaameaacaaIYaaabeaaliaaiYcacaWGQbWaaSbaaWqa
aiaaikdaaeqaaaWcbeaaaOqaaiaaysW7caaMe8UaaGjbVlaaysW7ca
aMe8UaaGjbVlaaysW7cqGHRaWkcaWGhbWaaWbaaSqabeaadaqadaqa
aiaaigdacaGGSaGaaGimaaGaayjkaiaawMcaaaaakmaabmaabaWaaq
GaaeaacaWG0bGaeyOeI0IaamyBamaaBaaaleaacaWGPbWaaSbaaWqa
aiaaigdaaeqaaaWcbeaakiaaykW7aiaawIa7aiaaykW7caWG4bWaaS
baaSqaaiaadQgadaWgaaadbaGaaGymaaqabaaaleqaaaGccaGLOaGa
ayzkaaGaam4ramaaCaaaleqabaWaaeWaaeaacaaIXaGaaiilaiaaic
daaiaawIcacaGLPaaaaaGcdaqadaqaamaaeiaabaGaamiDaiabgkHi
Tiaad2gadaWgaaWcbaGaamyAamaaBaaameaacaaIYaaabeaaaSqaba
GccaaMc8oacaGLiWoacaaMc8UaamiEamaaBaaaleaacaWGQbWaaSba
aWqaaiaaikdaaeqaaaWcbeaaaOGaayjkaiaawMcaaiaabogacaqGVb
GaaeODamaabmaabaGaamizamaaBaaaleaacaWGPbWaaSbaaWqaaiaa
igdaaeqaaSGaaGilaiaadQgadaWgaaadbaGaaGymaaqabaaaleqaaO
GaaGilaiaadsgadaWgaaWcbaGaamyAamaaBaaameaacaaIYaaabeaa
liaaiYcacaWGQbWaaSbaaWqaaiaaikdaaeqaaaWcbeaaaOGaayjkai
aawMcaaaqaaiaaysW7caaMe8UaaGjbVlaaysW7caaMe8UaaGjbVlaa
ysW7cqGHRaWkcaWGVbWaaSbaaSqaaiaadMgadaWgaaadbaGaaGymaa
qabaWccaaISaGaamyAamaaBaaameaacaaIYaaabeaaliaaiYcacaWG
QbWaaSbaaWqaaiaaigdaaeqaaSGaaGilaiaadQgadaWgaaadbaGaaG
OmaaqabaaaleqaaOWaaeWaaeaacqaH7oaBdaahaaWcbeqaaiaaisda
aaGccqGHRaWkdaqadaqaaiaad6gacqaH7oaBaiaawIcacaGLPaaada
ahaaWcbeqaaiabgkHiTiaaigdaaaaakiaawIcacaGLPaaacaaISaaa
aiaaywW7caaMf8UaaGzbVlaaywW7caaMf8UaaiikaiaacgeacaGGUa
GaaGymaiaaiwdacaGGPaaaaa@2076@
où
γ
i
,
j
:=
∫
−
∞
t
−
m
i
ε
d
G
(
ε
|
x
j
)
.
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacqaHZoWzda
WgaaWcbaGaamyAaiaaiYcacaWGQbaabeaakiaaiQdacaaI9aWaa8qm
aeqaleaacqGHsislcqGHEisPaeaacaWG0bGaeyOeI0IaamyBamaaBa
aameaacaWGPbaabeaaa0Gaey4kIipakiabew7aLjaadsgacaWGhbWa
aeWaaeaadaabcaqaaiabew7aLjaaykW7aiaawIa7aiaaykW7caWG4b
WaaSbaaSqaaiaadQgaaeqaaaGccaGLOaGaayzkaaGaaGOlaaaa@5482@
Observons maintenant que
b
i
,
j
1
,
j
2
=
w
j
1
,
j
2
−
w
i
,
j
2
+
O
i
,
j
1
,
j
2
(
(
n
λ
)
−
2
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWGIbWaaS
baaSqaaiaadMgacaaISaGaamOAamaaBaaameaacaaIXaaabeaaliaa
iYcacaWGQbWaaSbaaWqaaiaaikdaaeqaaaWcbeaakiaai2dacaWG3b
WaaSbaaSqaaiaadQgadaWgaaadbaGaaGymaaqabaWccaaISaGaamOA
amaaBaaameaacaaIYaaabeaaaSqabaGccqGHsislcaWG3bWaaSbaaS
qaaiaadMgacaaISaGaamOAamaaBaaameaacaaIYaaabeaaaSqabaGc
cqGHRaWkcaWGpbWaaSbaaSqaaiaadMgacaaISaGaamOAamaaBaaame
aacaaIXaaabeaaliaaiYcacaWGQbWaaSbaaWqaaiaaikdaaeqaaaWc
beaakmaabmaabaWaaeWaaeaacaWGUbGaeq4UdWgacaGLOaGaayzkaa
WaaWbaaSqabeaacqGHsislcaaIYaaaaaGccaGLOaGaayzkaaaaaa@5AEA@
et que
cov
(
d
i
1
,
j
1
,
d
i
2
,
j
2
)
=
1
c
i
1
,
j
1
c
i
2
,
j
2
∑
k
∈
s
;
k
≠
j
1
,
j
2
(
w
j
1
,
k
−
w
i
1
,
k
)
(
w
j
2
,
k
−
w
i
2
,
k
)
σ
k
2
=
∑
k
∈
s
(
w
j
1
,
k
−
w
i
1
,
k
)
(
w
j
2
,
k
−
w
i
2
,
k
)
σ
k
2
+
O
i
1
,
i
2
,
j
1
,
j
2
(
(
n
λ
)
−
2
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrVjFfea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaafaqaaeGaca
aabaGaae4yaiaab+gacaqG2bWaaeWaaeaacaWGKbWaaSbaaSqaaiaa
dMgadaWgaaadbaGaaGymaaqabaWccaaISaGaamOAamaaBaaameaaca
aIXaaabeaaaSqabaGccaaISaGaamizamaaBaaaleaacaWGPbWaaSba
aWqaaiaaikdaaeqaaSGaaGilaiaadQgadaWgaaadbaGaaGOmaaqaba
aaleqaaaGccaGLOaGaayzkaaaabaGaaGypamaalaaabaGaaGymaaqa
aiaadogadaWgaaWcbaGaamyAamaaBaaameaacaaIXaaabeaaliaaiY
cacaWGQbWaaSbaaWqaaiaaigdaaeqaaaWcbeaakiaadogadaWgaaWc
baGaamyAamaaBaaameaacaaIYaaabeaaliaaiYcacaWGQbWaaSbaaW
qaaiaaikdaaeqaaaWcbeaaaaGcdaaeqbqaamaabmaabaGaam4Damaa
BaaaleaacaWGQbWaaSbaaWqaaiaaigdaaeqaaSGaaGilaiaadUgaae
qaaOGaeyOeI0Iaam4DamaaBaaaleaacaWGPbWaaSbaaWqaaiaaigda
aeqaaSGaaGilaiaadUgaaeqaaaGccaGLOaGaayzkaaWaaeWaaeaaca
WG3bWaaSbaaSqaaiaadQgadaWgaaadbaGaaGOmaaqabaWccaaISaGa
am4AaaqabaGccqGHsislcaWG3bWaaSbaaSqaaiaadMgadaWgaaadba
GaaGOmaaqabaWccaaISaGaam4AaaqabaaakiaawIcacaGLPaaacqaH
dpWCdaqhaaWcbaGaam4AaaqaaiaaikdaaaaabaGaam4AaiabgIGiol
aadohacaaI7aGaam4AaiabgcMi5kaadQgadaWgaaadbaGaaGymaaqa
baWccaaISaGaamOAamaaBaaameaacaaIYaaabeaaaSqab0GaeyyeIu
oaaOqaaaqaaiaai2dadaaeqbqaamaabmaabaGaam4DamaaBaaaleaa
caWGQbWaaSbaaWqaaiaaigdaaeqaaSGaaGilaiaadUgaaeqaaOGaey
OeI0Iaam4DamaaBaaaleaacaWGPbWaaSbaaWqaaiaaigdaaeqaaSGa
aGilaiaadUgaaeqaaaGccaGLOaGaayzkaaWaaeWaaeaacaWG3bWaaS
baaSqaaiaadQgadaWgaaadbaGaaGOmaaqabaWccaaISaGaam4Aaaqa
baGccqGHsislcaWG3bWaaSbaaSqaaiaadMgadaWgaaadbaGaaGOmaa
qabaWccaaISaGaam4AaaqabaaakiaawIcacaGLPaaacqaHdpWCdaqh
aaWcbaGaam4AaaqaaiaaikdaaaaabaGaam4AaiabgIGiolaadohaae
qaniabggHiLdGccqGHRaWkcaWGpbWaaSbaaSqaaiaadMgadaWgaaad
baGaaGymaaqabaWccaaISaGaamyAamaaBaaameaacaaIYaaabeaali
aaiYcacaWGQbWaaSbaaWqaaiaaigdaaeqaaSGaaGilaiaadQgadaWg
aaadbaGaaGOmaaqabaaaleqaaOWaaeWaaeaadaqadaqaaiaad6gacq
aH7oaBaiaawIcacaGLPaaadaahaaWcbeqaaiabgkHiTiaaikdaaaaa
kiaawIcacaGLPaaaaaaaaa@B34A@
de sorte que
D
2
=
2
D
2
a
+
D
2
b
+
o
(
λ
5
+
n
−
1
)
,
(
A
.16
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWGebWaaS
baaSqaaiaaikdaaeqaaOGaaGypaiaaikdacaWGebWaaSbaaSqaaiaa
ikdacaWGHbaabeaakiabgUcaRiaadseadaWgaaWcbaGaaGOmaiaadk
gaaeqaaOGaey4kaSIaam4BamaabmaabaGaeq4UdW2aaWbaaSqabeaa
caaI1aaaaOGaey4kaSIaamOBamaaCaaaleqabaGaeyOeI0IaaGymaa
aaaOGaayjkaiaawMcaaiaaiYcacaaMf8UaaGzbVlaaywW7caaMf8Ua
aGzbVlaacIcacaGGbbGaaiOlaiaaigdacaaI2aGaaiykaaaa@57D7@
où
D
2
a
:=
1
N
2
∑
i
1
∉
s
∑
i
2
∉
s
∑
j
1
∈
s
∑
j
2
∈
s
,
j
2
≠
j
1
w
i
1
,
j
1
w
i
2
,
j
2
G
(
1
,
0
)
(
t
−
m
i
1
|
x
j
1
)
(
w
j
1
,
j
2
−
w
i
1
,
j
2
)
γ
i
2
,
j
2
=
1
N
2
∑
i
1
∉
s
∑
i
2
∉
s
∑
j
1
∈
s
∑
j
2
∈
s
w
i
1
,
j
1
w
i
2
,
j
2
G
(
1
,
0
)
(
t
−
m
i
1
|
x
j
1
)
(
w
j
1
,
j
2
−
w
i
1
,
j
2
)
γ
i
2
,
j
2
+
O
(
n
−
1
(
n
λ
)
−
1
)
=
1
N
2
∑
j
2
∈
s
G
(
1
,
0
)
(
t
−
m
j
2
|
x
j
2
)
γ
j
2
,
j
2
[
∑
j
1
∈
s
w
j
1
,
j
2
∑
i
1
∉
s
w
i
1
,
j
1
∑
i
2
∉
s
w
i
2
,
j
2
−
(
∑
i
∉
s
w
i
,
j
2
)
2
]
+
O
(
n
−
1
λ
+
n
−
1
(
n
λ
)
−
1
)
=
O
(
(
n
λ
)
−
1
α
+
n
−
1
λ
+
n
−
1
(
n
λ
)
−
1
)
(
A
.17
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrVjFfea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaafaqaaeqbca
aaaeaacaWGebWaaSbaaSqaaiaaikdacaWGHbaabeaaaOqaaiaaiQda
caaI9aWaaSaaaeaacaaIXaaabaGaamOtamaaCaaaleqabaGaaGOmaa
aaaaGcdaaeqbqaamaaqafabaWaaabuaeaadaaeqbqaaiaadEhadaWg
aaWcbaGaamyAamaaBaaameaacaaIXaaabeaaliaaiYcacaWGQbWaaS
baaWqaaiaaigdaaeqaaaWcbeaakiaadEhadaWgaaWcbaGaamyAamaa
BaaameaacaaIYaaabeaaliaaiYcacaWGQbWaaSbaaWqaaiaaikdaae
qaaaWcbeaakiaadEeadaahaaWcbeqaamaabmaabaGaaGymaiaacYca
caaIWaaacaGLOaGaayzkaaaaaaqaaiaadQgadaWgaaadbaGaaGOmaa
qabaWccqGHiiIZcaWGZbGaaGilaiaadQgadaWgaaadbaGaaGOmaaqa
baWccqGHGjsUcaWGQbWaaSbaaWqaaiaaigdaaeqaaaWcbeqdcqGHri
s5aaWcbaGaamOAamaaBaaameaacaaIXaaabeaaliabgIGiolaadoha
aeqaniabggHiLdaaleaacaWGPbWaaSbaaWqaaiaaikdaaeqaaSGaey
ycI8Saam4Caaqab0GaeyyeIuoaaSqaaiaadMgadaWgaaadbaGaaGym
aaqabaWccqGHjiYZcaWGZbaabeqdcqGHris5aOWaaeWaaeaadaabca
qaaiaadshacqGHsislcaWGTbWaaSbaaSqaaiaadMgadaWgaaadbaGa
aGymaaqabaaaleqaaOGaaGPaVdGaayjcSdGaaGPaVlaadIhadaWgaa
WcbaGaamOAamaaBaaameaacaaIXaaabeaaaSqabaaakiaawIcacaGL
PaaadaqadaqaaiaadEhadaWgaaWcbaGaamOAamaaBaaameaacaaIXa
aabeaaliaaiYcacaWGQbWaaSbaaWqaaiaaikdaaeqaaaWcbeaakiab
gkHiTiaadEhadaWgaaWcbaGaamyAamaaBaaameaacaaIXaaabeaali
aaiYcacaWGQbWaaSbaaWqaaiaaikdaaeqaaaWcbeaaaOGaayjkaiaa
wMcaaiabeo7aNnaaBaaaleaacaWGPbWaaSbaaWqaaiaaikdaaeqaaS
GaaGilaiaadQgadaWgaaadbaGaaGOmaaqabaaaleqaaaGcbaaabaGa
aGypamaalaaabaGaaGymaaqaaiaad6eadaahaaWcbeqaaiaaikdaaa
aaaOWaaabuaeaadaaeqbqaamaaqafabaWaaabuaeaacaWG3bWaaSba
aSqaaiaadMgadaWgaaadbaGaaGymaaqabaWccaaISaGaamOAamaaBa
aameaacaaIXaaabeaaaSqabaGccaWG3bWaaSbaaSqaaiaadMgadaWg
aaadbaGaaGOmaaqabaWccaaISaGaamOAamaaBaaameaacaaIYaaabe
aaaSqabaGccaWGhbWaaWbaaSqabeaadaqadaqaaiaaigdacaGGSaGa
aGimaaGaayjkaiaawMcaaaaaaeaacaWGQbWaaSbaaWqaaiaaikdaae
qaaSGaeyicI4Saam4Caaqab0GaeyyeIuoaaSqaaiaadQgadaWgaaad
baGaaGymaaqabaWccqGHiiIZcaWGZbaabeqdcqGHris5aaWcbaGaam
yAamaaBaaameaacaaIYaaabeaaliabgMGiplaadohaaeqaniabggHi
LdaaleaacaWGPbWaaSbaaWqaaiaaigdaaeqaaSGaeyycI8Saam4Caa
qab0GaeyyeIuoakmaabmaabaWaaqGaaeaacaWG0bGaeyOeI0IaamyB
amaaBaaaleaacaWGPbWaaSbaaWqaaiaaigdaaeqaaaWcbeaakiaayk
W7aiaawIa7aiaaykW7caWG4bWaaSbaaSqaaiaadQgadaWgaaadbaGa
aGymaaqabaaaleqaaaGccaGLOaGaayzkaaWaaeWaaeaacaWG3bWaaS
baaSqaaiaadQgadaWgaaadbaGaaGymaaqabaWccaaISaGaamOAamaa
BaaameaacaaIYaaabeaaaSqabaGccqGHsislcaWG3bWaaSbaaSqaai
aadMgadaWgaaadbaGaaGymaaqabaWccaaISaGaamOAamaaBaaameaa
caaIYaaabeaaaSqabaaakiaawIcacaGLPaaacqaHZoWzdaWgaaWcba
GaamyAamaaBaaameaacaaIYaaabeaaliaaiYcacaWGQbWaaSbaaWqa
aiaaikdaaeqaaaWcbeaakiabgUcaRiaad+eadaqadaqaaiaad6gada
ahaaWcbeqaaiabgkHiTiaaigdaaaGcdaqadaqaaiaad6gacqaH7oaB
aiaawIcacaGLPaaadaahaaWcbeqaaiabgkHiTiaaigdaaaaakiaawI
cacaGLPaaaaeaaaeaacaaI9aWaaSaaaeaacaaIXaaabaGaamOtamaa
CaaaleqabaGaaGOmaaaaaaGcdaaeqbqaaiaadEeadaahaaWcbeqaam
aabmaabaGaaGymaiaacYcacaaIWaaacaGLOaGaayzkaaaaaOWaaeWa
aeaadaabcaqaaiaadshacqGHsislcaWGTbWaaSbaaSqaaiaadQgada
WgaaadbaGaaGOmaaqabaaaleqaaOGaaGPaVdGaayjcSdGaaGPaVlaa
dIhadaWgaaWcbaGaamOAamaaBaaameaacaaIYaaabeaaaSqabaaaki
aawIcacaGLPaaacqaHZoWzdaWgaaWcbaGaamOAamaaBaaameaacaaI
YaaabeaaliaaiYcacaWGQbWaaSbaaWqaaiaaikdaaeqaaaWcbeaaae
aacaWGQbWaaSbaaWqaaiaaikdaaeqaaSGaeyicI4Saam4Caaqab0Ga
eyyeIuoakmaadmaabaWaaabuaeaacaWG3bWaaSbaaSqaaiaadQgada
WgaaadbaGaaGymaaqabaWccaaISaGaamOAamaaBaaameaacaaIYaaa
beaaaSqabaaabaGaamOAamaaBaaameaacaaIXaaabeaaliabgIGiol
aadohaaeqaniabggHiLdGcdaaeqbqaaiaadEhadaWgaaWcbaGaamyA
amaaBaaameaacaaIXaaabeaaliaaiYcacaWGQbWaaSbaaWqaaiaaig
daaeqaaaWcbeaaaeaacaWGPbWaaSbaaWqaaiaaigdaaeqaaSGaeyyc
I8Saam4Caaqab0GaeyyeIuoakmaaqafabaGaam4DamaaBaaaleaaca
WGPbWaaSbaaWqaaiaaikdaaeqaaSGaaGilaiaadQgadaWgaaadbaGa
aGOmaaqabaaaleqaaaqaaiaadMgadaWgaaadbaGaaGOmaaqabaWccq
GHjiYZcaWGZbaabeqdcqGHris5aOGaeyOeI0YaaeWaaeaadaaeqbqa
aiaadEhadaWgaaWcbaGaamyAaiaaiYcacaWGQbWaaSbaaWqaaiaaik
daaeqaaaWcbeaaaeaacaWGPbGaeyycI8Saam4Caaqab0GaeyyeIuoa
aOGaayjkaiaawMcaamaaCaaaleqabaGaaGOmaaaaaOGaay5waiaaw2
faaaqaaaqaaiaaysW7caaMe8Uaey4kaSIaam4tamaabmaabaGaamOB
amaaCaaaleqabaGaeyOeI0IaaGymaaaakiabeU7aSjabgUcaRiaad6
gadaahaaWcbeqaaiabgkHiTiaaigdaaaGcdaqadaqaaiaad6gacqaH
7oaBaiaawIcacaGLPaaadaahaaWcbeqaaiabgkHiTiaaigdaaaaaki
aawIcacaGLPaaaaeaaaeaacaaI9aGaam4tamaabmaabaWaaeWaaeaa
caWGUbGaeq4UdWgacaGLOaGaayzkaaWaaWbaaSqabeaacqGHsislca
aIXaaaaOGaeqySdeMaey4kaSIaamOBamaaCaaaleqabaGaeyOeI0Ia
aGymaaaakiabeU7aSjabgUcaRiaad6gadaahaaWcbeqaaiabgkHiTi
aaigdaaaGcdaqadaqaaiaad6gacqaH7oaBaiaawIcacaGLPaaadaah
aaWcbeqaaiabgkHiTiaaigdaaaaakiaawIcacaGLPaaaaaGaaGzbVl
aaywW7caGGOaGaaiyqaiaac6cacaaIXaGaaG4naiaacMcaaaa@7AC7@
et
D
2
b
:=
1
N
2
∑
i
1
∉
s
∑
i
2
∉
s
∑
j
1
∈
s
∑
j
2
∈
s
,
j
2
≠
j
1
w
i
1
,
j
1
w
i
2
,
j
2
G
(
1
,
0
)
(
t
−
m
i
1
|
x
j
1
)
G
(
1
,
0
)
(
t
−
m
i
2
|
x
j
2
)
×
∑
k
∈
s
(
w
j
1
,
k
−
w
i
1
,
k
)
(
w
j
2
,
k
−
w
i
2
,
k
)
σ
k
2
=
1
N
2
∑
i
1
∉
s
∑
i
2
∉
s
∑
j
1
∈
s
∑
j
2
∈
s
w
i
1
,
j
1
w
i
2
,
j
2
G
(
1
,
0
)
(
t
−
m
i
1
|
x
j
1
)
G
(
1
,
0
)
(
t
−
m
i
2
|
x
j
2
)
×
∑
k
∈
s
(
w
j
1
,
k
−
w
i
1
,
k
)
(
w
j
2
,
k
−
w
i
2
,
k
)
σ
k
2
+
O
(
n
−
1
(
n
λ
)
−
1
)
=
1
N
2
∑
k
∈
s
σ
k
2
[
G
(
1
,
0
)
(
t
−
m
k
|
x
k
)
]
2
(
∑
i
∉
s
∑
j
∈
s
w
i
,
j
(
w
j
,
k
−
w
i
,
k
)
)
2
+
O
(
n
−
1
λ
+
n
−
1
(
n
λ
)
−
1
)
=
1
N
2
∑
k
∈
s
σ
k
2
[
G
(
1
,
0
)
(
t
−
m
k
|
x
k
)
]
2
(
∑
j
∈
s
w
j
,
k
∑
i
∉
s
w
i
,
j
−
∑
i
∉
s
w
i
,
k
)
2
+
O
(
n
−
1
λ
+
n
−
1
(
n
λ
)
−
1
)
=
O
(
(
n
λ
)
−
1
α
+
n
−
1
λ
)
.
(
A
.18
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrVjFfea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaafaqaaeWbca
aaaeaacaWGebWaaSbaaSqaaiaaikdacaWGIbaabeaaaOqaaiaaiQda
caaI9aWaaSaaaeaacaaIXaaabaGaamOtamaaCaaaleqabaGaaGOmaa
aaaaGcdaaeqbqaamaaqafabaWaaabuaeaadaaeqbqaaiaadEhadaWg
aaWcbaGaamyAamaaBaaameaacaaIXaaabeaaliaaiYcacaWGQbWaaS
baaWqaaiaaigdaaeqaaaWcbeaakiaadEhadaWgaaWcbaGaamyAamaa
BaaameaacaaIYaaabeaaliaaiYcacaWGQbWaaSbaaWqaaiaaikdaae
qaaaWcbeaakiaadEeadaahaaWcbeqaamaabmaabaGaaGymaiaacYca
caaIWaaacaGLOaGaayzkaaaaaaqaaiaadQgadaWgaaadbaGaaGOmaa
qabaWccqGHiiIZcaWGZbGaaGilaiaadQgadaWgaaadbaGaaGOmaaqa
baWccqGHGjsUcaWGQbWaaSbaaWqaaiaaigdaaeqaaaWcbeqdcqGHri
s5aaWcbaGaamOAamaaBaaameaacaaIXaaabeaaliabgIGiolaadoha
aeqaniabggHiLdaaleaacaWGPbWaaSbaaWqaaiaaikdaaeqaaSGaey
ycI8Saam4Caaqab0GaeyyeIuoaaSqaaiaadMgadaWgaaadbaGaaGym
aaqabaWccqGHjiYZcaWGZbaabeqdcqGHris5aOWaaeWaaeaadaabca
qaaiaadshacqGHsislcaWGTbWaaSbaaSqaaiaadMgadaWgaaadbaGa
aGymaaqabaaaleqaaOGaaGPaVdGaayjcSdGaaGPaVlaadIhadaWgaa
WcbaGaamOAamaaBaaameaacaaIXaaabeaaaSqabaaakiaawIcacaGL
PaaacaWGhbWaaWbaaSqabeaadaqadaqaaiaaigdacaGGSaGaaGimaa
GaayjkaiaawMcaaaaakmaabmaabaWaaqGaaeaacaWG0bGaeyOeI0Ia
amyBamaaBaaaleaacaWGPbWaaSbaaWqaaiaaikdaaeqaaaWcbeaaki
aaykW7aiaawIa7aiaaykW7caWG4bWaaSbaaSqaaiaadQgadaWgaaad
baGaaGOmaaqabaaaleqaaaGccaGLOaGaayzkaaaabaaabaGaaGjbVl
aaysW7caaMe8UaaGjbVlabgEna0oaaqafabaWaaeWaaeaacaWG3bWa
aSbaaSqaaiaadQgadaWgaaadbaGaaGymaaqabaWccaaISaGaam4Aaa
qabaGccqGHsislcaWG3bWaaSbaaSqaaiaadMgadaWgaaadbaGaaGym
aaqabaWccaaISaGaam4AaaqabaaakiaawIcacaGLPaaadaqadaqaai
aadEhadaWgaaWcbaGaamOAamaaBaaameaacaaIYaaabeaaliaaiYca
caWGRbaabeaakiabgkHiTiaadEhadaWgaaWcbaGaamyAamaaBaaame
aacaaIYaaabeaaliaaiYcacaWGRbaabeaaaOGaayjkaiaawMcaaiab
eo8aZnaaDaaaleaacaWGRbaabaGaaGOmaaaaaeaacaWGRbGaeyicI4
Saam4Caaqab0GaeyyeIuoaaOqaaaqaaiaai2dadaWcaaqaaiaaigda
aeaacaWGobWaaWbaaSqabeaacaaIYaaaaaaakmaaqafabaWaaabuae
aadaaeqbqaamaaqafabaGaam4DamaaBaaaleaacaWGPbWaaSbaaWqa
aiaaigdaaeqaaSGaaGilaiaadQgadaWgaaadbaGaaGymaaqabaaale
qaaOGaam4DamaaBaaaleaacaWGPbWaaSbaaWqaaiaaikdaaeqaaSGa
aGilaiaadQgadaWgaaadbaGaaGOmaaqabaaaleqaaOGaam4ramaaCa
aaleqabaWaaeWaaeaacaaIXaGaaiilaiaaicdaaiaawIcacaGLPaaa
aaaabaGaamOAamaaBaaameaacaaIYaaabeaaliabgIGiolaadohaae
qaniabggHiLdaaleaacaWGQbWaaSbaaWqaaiaaigdaaeqaaSGaeyic
I4Saam4Caaqab0GaeyyeIuoaaSqaaiaadMgadaWgaaadbaGaaGOmaa
qabaWccqGHjiYZcaWGZbaabeqdcqGHris5aaWcbaGaamyAamaaBaaa
meaacaaIXaaabeaaliabgMGiplaadohaaeqaniabggHiLdGcdaqada
qaamaaeiaabaGaamiDaiabgkHiTiaad2gadaWgaaWcbaGaamyAamaa
BaaameaacaaIXaaabeaaaSqabaGccaaMc8oacaGLiWoacaaMc8Uaam
iEamaaBaaaleaacaWGQbWaaSbaaWqaaiaaigdaaeqaaaWcbeaaaOGa
ayjkaiaawMcaaiaadEeadaahaaWcbeqaamaabmaabaGaaGymaiaacY
cacaaIWaaacaGLOaGaayzkaaaaaOWaaeWaaeaadaabcaqaaiaadsha
cqGHsislcaWGTbWaaSbaaSqaaiaadMgadaWgaaadbaGaaGOmaaqaba
aaleqaaOGaaGPaVdGaayjcSdGaaGPaVlaadIhadaWgaaWcbaGaamOA
amaaBaaameaacaaIYaaabeaaaSqabaaakiaawIcacaGLPaaaaeaaae
aacaaMe8UaaGjbVlaaysW7caaMe8Uaey41aq7aaabuaeaadaqadaqa
aiaadEhadaWgaaWcbaGaamOAamaaBaaameaacaaIXaaabeaaliaaiY
cacaWGRbaabeaakiabgkHiTiaadEhadaWgaaWcbaGaamyAamaaBaaa
meaacaaIXaaabeaaliaaiYcacaWGRbaabeaaaOGaayjkaiaawMcaam
aabmaabaGaam4DamaaBaaaleaacaWGQbWaaSbaaWqaaiaaikdaaeqa
aSGaaGilaiaadUgaaeqaaOGaeyOeI0Iaam4DamaaBaaaleaacaWGPb
WaaSbaaWqaaiaaikdaaeqaaSGaaGilaiaadUgaaeqaaaGccaGLOaGa
ayzkaaGaeq4Wdm3aa0baaSqaaiaadUgaaeaacaaIYaaaaaqaaiaadU
gacqGHiiIZcaWGZbaabeqdcqGHris5aOGaey4kaSIaam4tamaabmaa
baGaamOBamaaCaaaleqabaGaeyOeI0IaaGymaaaakmaabmaabaGaam
OBaiabeU7aSbGaayjkaiaawMcaamaaCaaaleqabaGaeyOeI0IaaGym
aaaaaOGaayjkaiaawMcaaaqaaaqaaiaai2dadaWcaaqaaiaaigdaae
aacaWGobWaaWbaaSqabeaacaaIYaaaaaaakmaaqafabaGaeq4Wdm3a
a0baaSqaaiaadUgaaeaacaaIYaaaaOWaamWaaeaacaWGhbWaaWbaaS
qabeaadaqadaqaaiaaigdacaGGSaGaaGimaaGaayjkaiaawMcaaaaa
kmaabmaabaWaaqGaaeaacaWG0bGaeyOeI0IaamyBamaaBaaaleaaca
WGRbaabeaakiaaykW7aiaawIa7aiaaykW7caWG4bWaaSbaaSqaaiaa
dUgaaeqaaaGccaGLOaGaayzkaaaacaGLBbGaayzxaaWaaWbaaSqabe
aacaaIYaaaaaqaaiaadUgacqGHiiIZcaWGZbaabeqdcqGHris5aOWa
aeWaaeaadaaeqbqaamaaqafabaGaam4DamaaBaaaleaacaWGPbGaaG
ilaiaadQgaaeqaaOWaaeWaaeaacaWG3bWaaSbaaSqaaiaadQgacaaI
SaGaam4AaaqabaGccqGHsislcaWG3bWaaSbaaSqaaiaadMgacaaISa
Gaam4AaaqabaaakiaawIcacaGLPaaaaSqaaiaadQgacqGHiiIZcaWG
ZbaabeqdcqGHris5aaWcbaGaamyAaiabgMGiplaadohaaeqaniabgg
HiLdaakiaawIcacaGLPaaadaahaaWcbeqaaiaaikdaaaGccqGHRaWk
caWGpbWaaeWaaeaacaWGUbWaaWbaaSqabeaacqGHsislcaaIXaaaaO
Gaeq4UdWMaey4kaSIaamOBamaaCaaaleqabaGaeyOeI0IaaGymaaaa
kmaabmaabaGaamOBaiabeU7aSbGaayjkaiaawMcaamaaCaaaleqaba
GaeyOeI0IaaGymaaaaaOGaayjkaiaawMcaaaqaaaqaaiaai2dadaWc
aaqaaiaaigdaaeaacaWGobWaaWbaaSqabeaacaaIYaaaaaaakmaaqa
fabaGaeq4Wdm3aa0baaSqaaiaadUgaaeaacaaIYaaaaOWaamWaaeaa
caWGhbWaaWbaaSqabeaadaqadaqaaiaaigdacaGGSaGaaGimaaGaay
jkaiaawMcaaaaakmaabmaabaWaaqGaaeaacaWG0bGaeyOeI0IaamyB
amaaBaaaleaacaWGRbaabeaakiaaykW7aiaawIa7aiaaykW7caWG4b
WaaSbaaSqaaiaadUgaaeqaaaGccaGLOaGaayzkaaaacaGLBbGaayzx
aaWaaWbaaSqabeaacaaIYaaaaaqaaiaadUgacqGHiiIZcaWGZbaabe
qdcqGHris5aOWaaeWaaeaadaaeqbqaaiaadEhadaWgaaWcbaGaamOA
aiaaiYcacaWGRbaabeaakmaaqafabaGaam4DamaaBaaaleaacaWGPb
GaaGilaiaadQgaaeqaaOGaeyOeI0YaaabuaeaacaWG3bWaaSbaaSqa
aiaadMgacaaISaGaam4AaaqabaaabaGaamyAaiabgMGiplaadohaae
qaniabggHiLdaaleaacaWGPbGaeyycI8Saam4Caaqab0GaeyyeIuoa
aSqaaiaadQgacqGHiiIZcaWGZbaabeqdcqGHris5aaGccaGLOaGaay
zkaaWaaWbaaSqabeaacaaIYaaaaOGaey4kaSIaam4tamaabmaabaGa
amOBamaaCaaaleqabaGaeyOeI0IaaGymaaaakiabeU7aSjabgUcaRi
aad6gadaahaaWcbeqaaiabgkHiTiaaigdaaaGcdaqadaqaaiaad6ga
cqaH7oaBaiaawIcacaGLPaaadaahaaWcbeqaaiabgkHiTiaaigdaaa
aakiaawIcacaGLPaaaaeaaaeaacaaI9aGaam4tamaabmaabaWaaeWa
aeaacaWGUbGaeq4UdWgacaGLOaGaayzkaaWaaWbaaSqabeaacqGHsi
slcaaIXaaaaOGaeqySdeMaey4kaSIaamOBamaaCaaaleqabaGaeyOe
I0IaaGymaaaakiabeU7aSbGaayjkaiaawMcaaiaai6caaaGaaGzbVl
aaywW7caGGOaGaaiyqaiaac6cacaaIXaGaaGioaiaacMcaaaa@F4DA@
En regroupant tout, on obtient
finalement
var
(
F
^
*
(
t
)
−
F
N
(
t
)
)
=
1
n
(
N
−
n
N
)
2
∫
a
b
[
G
(
t
−
m
(
x
)
|
x
)
−
G
2
(
t
−
m
(
x
)
|
x
)
]
[
h
s
¯
(
x
)
/
h
s
(
x
)
]
h
s
¯
(
x
)
d
x
+
1
N
−
n
(
N
−
n
N
)
2
∫
a
b
[
G
(
t
−
m
(
x
)
|
x
)
−
G
2
(
t
−
m
(
x
)
|
x
)
]
h
s
¯
(
x
)
d
x
+
o
(
λ
5
+
n
−
1
)
.
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaafaqaaeGaca
aabaGaaeODaiaabggacaqGYbWaaeWaaeaaceWGgbGbaKaadaahaaWc
beqaaiaaiQcaaaGccaaMb8+aaeWaaeaacaWG0baacaGLOaGaayzkaa
GaeyOeI0IaamOramaaBaaaleaacaWGobaabeaakmaabmaabaGaamiD
aaGaayjkaiaawMcaaaGaayjkaiaawMcaaaqaaiaai2dadaWcaaqaai
aaigdaaeaacaWGUbaaamaabmaabaWaaSaaaeaacaWGobGaeyOeI0Ia
amOBaaqaaiaad6eaaaaacaGLOaGaayzkaaWaaWbaaSqabeaacaaIYa
aaaOWaa8qmaeqaleaacaWGHbaabaGaamOyaaqdcqGHRiI8aOWaamWa
aeaacaWGhbWaaeWaaeaadaabcaqaaiaadshacqGHsislcaWGTbWaae
WaaeaacaWG4baacaGLOaGaayzkaaGaaGPaVdGaayjcSdGaaGPaVlaa
dIhaaiaawIcacaGLPaaacqGHsislcaWGhbWaaWbaaSqabeaacaaIYa
aaaOWaaeWaaeaadaabcaqaaiaadshacqGHsislcaWGTbWaaeWaaeaa
caWG4baacaGLOaGaayzkaaGaaGPaVdGaayjcSdGaaGPaVlaadIhaai
aawIcacaGLPaaaaiaawUfacaGLDbaadaWadaqaamaalyaabaGaamiA
amaaBaaaleaacaaMc8Uabm4CayaaraaabeaakmaabmaabaGaamiEaa
GaayjkaiaawMcaaaqaaiaadIgadaWgaaWcbaGaam4CaaqabaGcdaqa
daqaaiaadIhaaiaawIcacaGLPaaaaaaacaGLBbGaayzxaaGaamiAam
aaBaaaleaacaaMc8Uabm4CayaaraaabeaakmaabmaabaGaamiEaaGa
ayjkaiaawMcaaiaadsgacaWG4baabaaabaGaaGjbVlaaysW7cqGHRa
WkdaWcaaqaaiaaigdaaeaacaWGobGaeyOeI0IaamOBaaaadaqadaqa
amaalaaabaGaamOtaiabgkHiTiaad6gaaeaacaWGobaaaaGaayjkai
aawMcaamaaCaaaleqabaGaaGOmaaaakmaapedabeWcbaGaamyyaaqa
aiaadkgaa0Gaey4kIipakmaadmaabaGaam4ramaabmaabaWaaqGaae
aacaWG0bGaeyOeI0IaamyBamaabmaabaGaamiEaaGaayjkaiaawMca
aiaaykW7aiaawIa7aiaaykW7caWG4baacaGLOaGaayzkaaGaeyOeI0
Iaam4ramaaCaaaleqabaGaaGOmaaaakmaabmaabaWaaqGaaeaacaWG
0bGaeyOeI0IaamyBamaabmaabaGaamiEaaGaayjkaiaawMcaaiaayk
W7aiaawIa7aiaaykW7caWG4baacaGLOaGaayzkaaaacaGLBbGaayzx
aaGaamiAamaaBaaaleaacaaMc8Uabm4Cayaaraaabeaakmaabmaaba
GaamiEaaGaayjkaiaawMcaaiaadsgacaWG4bGaey4kaSIaam4Bamaa
bmaabaGaeq4UdW2aaWbaaSqabeaacaaI1aaaaOGaey4kaSIaamOBam
aaCaaaleqabaGaeyOeI0IaaGymaaaaaOGaayjkaiaawMcaaiaai6ca
aaaaaa@CA5E@
Variance de
l’estimateur par la différence généralisée avec valeurs prédites modifiées
Étant donné (A.7), nous allons montrer
que
var
(
F
˜
*
(
t
)
−
F
N
(
t
)
)
=
var
(
F
^
*
(
t
)
−
F
N
(
t
)
)
+
o
(
n
−
1
)
(
A
.19
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaqG2bGaae
yyaiaabkhadaqadaqaaiqadAeagaacamaaCaaaleqabaGaaGOkaaaa
kiaaygW7daqadaqaaiaadshaaiaawIcacaGLPaaacqGHsislcaWGgb
WaaSbaaSqaaiaad6eaaeqaaOWaaeWaaeaacaWG0baacaGLOaGaayzk
aaaacaGLOaGaayzkaaGaaGypaiaabAhacaqGHbGaaeOCamaabmaaba
GabmOrayaajaWaaWbaaSqabeaacaaIQaaaaOGaaGzaVpaabmaabaGa
amiDaaGaayjkaiaawMcaaiabgkHiTiaadAeadaWgaaWcbaGaamOtaa
qabaGcdaqadaqaaiaadshaaiaawIcacaGLPaaaaiaawIcacaGLPaaa
cqGHRaWkcaWGVbWaaeWaaeaacaWGUbWaaWbaaSqabeaacqGHsislca
aIXaaaaaGccaGLOaGaayzkaaGaaGzbVlaaywW7caaMf8UaaGzbVlaa
ywW7caGGOaGaaiyqaiaac6cacaaIXaGaaGyoaiaacMcaaaa@69DB@
en démontrant que
var
(
1
N
∑
i
∈
s
(
1
−
π
i
−
1
)
∑
j
∈
s
w
˜
i
,
j
(
I
(
ε
j
≤
t
−
m
i
+
d
˜
i
,
j
)
−
I
(
y
i
≤
t
)
)
)
=
o
(
n
−
1
)
.
(
A
.20
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaqG2bGaae
yyaiaabkhadaqadaqaamaalaaabaGaaGymaaqaaiaad6eaaaWaaabu
aeqaleaacaWGPbGaeyicI4Saam4Caaqab0GaeyyeIuoakmaabmaaba
GaaGymaiabgkHiTiabec8aWnaaDaaaleaacaWGPbaabaGaeyOeI0Ia
aGymaaaaaOGaayjkaiaawMcaamaaqafabaGabm4DayaaiaWaaSbaaS
qaaiaadMgacaaISaGaamOAaaqabaaabaGaamOAaiabgIGiolaadoha
aeqaniabggHiLdGcdaqadaqaaiaadMeadaqadaqaaiabew7aLnaaBa
aaleaacaWGQbaabeaakiabgsMiJkaadshacqGHsislcaWGTbWaaSba
aSqaaiaadMgaaeqaaOGaey4kaSIabmizayaaiaWaaSbaaSqaaiaadM
gacaaISaGaamOAaaqabaaakiaawIcacaGLPaaacqGHsislcaWGjbWa
aeWaaeaacaWG5bWaaSbaaSqaaiaadMgaaeqaaOGaeyizImQaamiDaa
GaayjkaiaawMcaaaGaayjkaiaawMcaaaGaayjkaiaawMcaaiaai2da
caWGVbWaaeWaaeaacaWGUbWaaWbaaSqabeaacqGHsislcaaIXaaaaa
GccaGLOaGaayzkaaGaaGOlaiaaywW7caaMf8UaaGzbVlaaywW7caaM
f8UaaiikaiaacgeacaGGUaGaaGOmaiaaicdacaGGPaaaaa@8081@
Pour prouver (A.20), observons que la
variance dans le premier membre peut s’écrire
E
1
+
E
2
+
E
3
−
2
E
4
−
2
E
5
,
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWGfbWaaS
baaSqaaiaaigdaaeqaaOGaey4kaSIaamyramaaBaaaleaacaaIYaaa
beaakiabgUcaRiaadweadaWgaaWcbaGaaG4maaqabaGccqGHsislca
aIYaGaamyramaaBaaaleaacaaI0aaabeaakiabgkHiTiaaikdacaWG
fbWaaSbaaSqaaiaaiwdaaeqaaOGaaGilaaaa@466D@
où
E
1
:=
1
N
2
∑
i
1
∈
s
∑
i
2
∈
s
∑
j
∈
s
w
˜
i
1
,
j
w
˜
i
2
,
j
(
1
−
π
i
1
−
1
)
(
1
−
π
i
2
−
1
)
×
cov
(
I
(
ε
j
≤
t
−
m
i
1
+
d
˜
i
1
,
j
)
,
I
(
ε
j
≤
t
−
m
i
2
+
d
˜
i
2
,
j
)
)
,
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWGfbWaaS
baaSqaaiaaigdaaeqaaOGaaGOoaiaai2dadaWcaaqaaiaaigdaaeaa
caWGobWaaWbaaSqabeaacaaIYaaaaaaakmaaqafabaWaaabuaeaada
aeqbqaaiqadEhagaacamaaBaaaleaacaWGPbWaaSbaaWqaaiaaigda
aeqaaSGaaGilaiaadQgaaeqaaOGabm4DayaaiaWaaSbaaSqaaiaadM
gadaWgaaadbaGaaGOmaaqabaWccaaISaGaamOAaaqabaaabaGaamOA
aiabgIGiolaadohaaeqaniabggHiLdaaleaacaWGPbWaaSbaaWqaai
aaikdaaeqaaSGaeyicI4Saam4Caaqab0GaeyyeIuoaaSqaaiaadMga
daWgaaadbaGaaGymaaqabaWccqGHiiIZcaWGZbaabeqdcqGHris5aO
WaaeWaaeaacaaIXaGaeyOeI0IaeqiWda3aa0baaSqaaiaadMgadaWg
aaadbaGaaGymaaqabaaaleaacqGHsislcaaIXaaaaaGccaGLOaGaay
zkaaWaaeWaaeaacaaIXaGaeyOeI0IaeqiWda3aa0baaSqaaiaadMga
daWgaaadbaGaaGOmaaqabaaaleaacqGHsislcaaIXaaaaaGccaGLOa
GaayzkaaGaey41aqRaae4yaiaab+gacaqG2bWaaeWaaeaacaWGjbWa
aeWaaeaacqaH1oqzdaWgaaWcbaGaamOAaaqabaGccqGHKjYOcaWG0b
GaeyOeI0IaamyBamaaBaaaleaacaWGPbWaaSbaaeaacaaIXaaabeaa
aeqaaOGaey4kaSIabmizayaaiaWaaSbaaSqaaiaadMgadaWgaaadba
GaaGymaaqabaWccaaISaGaamOAaaqabaaakiaawIcacaGLPaaacaaI
SaGaamysamaabmaabaGaeqyTdu2aaSbaaSqaaiaadQgaaeqaaOGaey
izImQaamiDaiabgkHiTiaad2gadaWgaaWcbaGaamyAamaaBaaameaa
caaIYaaabeaaaSqabaGccqGHRaWkceWGKbGbaGaadaWgaaWcbaGaam
yAamaaBaaameaacaaIYaaabeaaliaaiYcacaWGQbaabeaaaOGaayjk
aiaawMcaaaGaayjkaiaawMcaaiaaiYcaaaa@95B9@
E
2
:=
1
N
2
∑
i
1
∈
s
∑
i
2
∈
s
∑
j
1
∈
s
∑
j
2
∈
s
,
j
2
≠
j
1
w
˜
i
1
,
j
w
˜
i
2
,
j
2
(
1
−
π
i
1
−
1
)
(
1
−
π
i
2
−
1
)
×
cov
(
I
(
ε
j
1
≤
t
−
m
i
1
+
d
˜
i
1
,
j
1
)
,
I
(
ε
j
2
≤
t
−
m
i
2
+
d
˜
i
2
,
j
2
)
)
,
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peea0dXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWGfbWaaS
baaSqaaiaaikdaaeqaaOGaaGOoaiaai2dadaWcaaqaaiaaigdaaeaa
caWGobWaaWbaaSqabeaacaaIYaaaaaaakmaaqafabaWaaabuaeaada
aeqbqaamaaqafabaGabm4DayaaiaWaaSbaaSqaaiaadMgadaWgaaad
baGaaGymaaqabaWccaaISaGaamOAaaqabaGcceWG3bGbaGaadaWgaa
WcbaGaamyAamaaBaaameaacaaIYaaabeaaliaaiYcacaWGQbWaaSba
aWqaaiaaikdaaeqaaaWcbeaaaeaacaWGQbWaaSbaaWqaaiaaikdaae
qaaSGaeyicI4Saam4CaiaaiYcacaWGQbWaaSbaaWqaaiaaikdaaeqa
aSGaeyiyIKRaamOAamaaBaaameaacaaIXaaabeaaaSqab0GaeyyeIu
oaaSqaaiaadQgadaWgaaadbaGaaGymaaqabaWccqGHiiIZcaWGZbaa
beqdcqGHris5aaWcbaGaamyAamaaBaaameaacaaIYaaabeaaliabgI
GiolaadohaaeqaniabggHiLdaaleaacaWGPbWaaSbaaWqaaiaaigda
aeqaaSGaeyicI4Saam4Caaqab0GaeyyeIuoakmaabmaabaGaaGymai
abgkHiTiabec8aWnaaDaaaleaacaWGPbWaaSbaaWqaaiaaigdaaeqa
aaWcbaGaeyOeI0IaaGymaaaaaOGaayjkaiaawMcaamaabmaabaGaaG
ymaiabgkHiTiabec8aWnaaDaaaleaacaWGPbWaaSbaaWqaaiaaikda
aeqaaaWcbaGaeyOeI0IaaGymaaaaaOGaayjkaiaawMcaaiabgEna0k
aabogacaqGVbGaaeODamaabmaabaGaamysamaabmaabaGaeqyTdu2a
aSbaaSqaaiaadQgadaWgaaadbaGaaGymaaqabaaaleqaaOGaeyizIm
QaamiDaiabgkHiTiaad2gadaWgaaWcbaGaamyAamaaBaaameaacaaI
XaaabeaaaSqabaGccqGHRaWkceWGKbGbaGaadaWgaaWcbaGaamyAam
aaBaaameaacaaIXaaabeaaliaaiYcacaWGQbWaaSbaaWqaaiaaigda
aeqaaaWcbeaaaOGaayjkaiaawMcaaiaaiYcacaWGjbWaaeWaaeaacq
aH1oqzdaWgaaWcbaGaamOAamaaBaaameaacaaIYaaabeaaaSqabaGc
cqGHKjYOcaWG0bGaeyOeI0IaamyBamaaBaaaleaacaWGPbWaaSbaaW
qaaiaaikdaaeqaaaWcbeaakiabgUcaRiqadsgagaacamaaBaaaleaa
caWGPbWaaSbaaWqaaiaaikdaaeqaaSGaaGilaiaadQgadaWgaaadba
GaaGOmaaqabaaaleqaaaGccaGLOaGaayzkaaaacaGLOaGaayzkaaGa
aGilaaaa@A839@
E
3
:=
1
N
2
∑
i
∈
s
(
1
−
π
i
−
1
)
2
var
(
I
(
ε
i
≤
t
−
m
i
)
)
,
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaafaqaaeqaca
aabaGaamyramaaBaaaleaacaaIZaaabeaaaOqaaiaaiQdacaaI9aWa
aSaaaeaacaaIXaaabaGaamOtamaaCaaaleqabaGaaGOmaaaaaaGcda
aeqbqabSqaaiaadMgacqGHiiIZcaWGZbaabeqdcqGHris5aOWaaeWa
aeaacaaIXaGaeyOeI0IaeqiWda3aa0baaSqaaiaadMgaaeaacqGHsi
slcaaIXaaaaaGccaGLOaGaayzkaaWaaWbaaSqabeaacaaIYaaaaOGa
aeODaiaabggacaqGYbWaaeWaaeaacaWGjbWaaeWaaeaacqaH1oqzda
WgaaWcbaGaamyAaaqabaGccqGHKjYOcaWG0bGaeyOeI0IaamyBamaa
BaaaleaacaWGPbaabeaaaOGaayjkaiaawMcaaaGaayjkaiaawMcaai
aaiYcaaaaaaa@5BFF@
E
4
:=
1
N
2
∑
i
∈
s
∑
j
∈
s
w
˜
i
1
,
j
(
1
−
π
i
−
1
)
(
1
−
π
j
−
1
)
cov
(
I
(
ε
j
≤
t
−
m
i
+
d
˜
i
,
j
)
,
I
(
ε
j
≤
t
−
m
j
)
)
,
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaafaqaaeqaca
aabaGaamyramaaBaaaleaacaaI0aaabeaaaOqaaiaaiQdacaaI9aWa
aSaaaeaacaaIXaaabaGaamOtamaaCaaaleqabaGaaGOmaaaaaaGcda
aeqbqabSqaaiaadMgacqGHiiIZcaWGZbaabeqdcqGHris5aOWaaabu
aeaaceWG3bGbaGaadaWgaaWcbaGaamyAamaaBaaameaacaaIXaaabe
aaliaaiYcacaWGQbaabeaaaeaacaWGQbGaeyicI4Saam4Caaqab0Ga
eyyeIuoakmaabmaabaGaaGymaiabgkHiTiabec8aWnaaDaaaleaaca
WGPbaabaGaeyOeI0IaaGymaaaaaOGaayjkaiaawMcaamaabmaabaGa
aGymaiabgkHiTiabec8aWnaaDaaaleaacaWGQbaabaGaeyOeI0IaaG
ymaaaaaOGaayjkaiaawMcaaiaabogacaqGVbGaaeODamaabmaabaGa
amysamaabmaabaGaeqyTdu2aaSbaaSqaaiaadQgaaeqaaOGaeyizIm
QaamiDaiabgkHiTiaad2gadaWgaaWcbaGaamyAaaqabaGccqGHRaWk
ceWGKbGbaGaadaWgaaWcbaGaamyAaiaaiYcacaWGQbaabeaaaOGaay
jkaiaawMcaaiaaiYcacaWGjbWaaeWaaeaacqaH1oqzdaWgaaWcbaGa
amOAaaqabaGccqGHKjYOcaWG0bGaeyOeI0IaamyBamaaBaaaleaaca
WGQbaabeaaaOGaayjkaiaawMcaaaGaayjkaiaawMcaaiaaiYcaaaaa
aa@7D41@
et finalement
E
5
:=
1
N
2
∑
i
1
∈
s
∑
i
2
∈
s
∑
j
∈
s
,
j
≠
i
2
w
˜
i
1
,
j
(
1
−
π
i
1
−
1
)
(
1
−
π
i
2
−
1
)
×
cov
(
I
(
ε
j
≤
t
−
m
i
1
+
d
˜
i
1
,
j
)
,
I
(
ε
i
2
≤
t
−
m
i
2
)
)
.
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWGfbWaaS
baaSqaaiaaiwdaaeqaaOGaaGOoaiaai2dadaWcaaqaaiaaigdaaeaa
caWGobWaaWbaaSqabeaacaaIYaaaaaaakmaaqafabaWaaabuaeaada
aeqbqaaiqadEhagaacamaaBaaaleaacaWGPbWaaSbaaWqaaiaaigda
aeqaaSGaaGilaiaadQgaaeqaaaqaaiaadQgacqGHiiIZcaWGZbGaaG
ilaiaadQgacqGHGjsUcaWGPbWaaSbaaWqaaiaaikdaaeqaaaWcbeqd
cqGHris5aaWcbaGaamyAamaaBaaameaacaaIYaaabeaaliabgIGiol
aadohaaeqaniabggHiLdaaleaacaWGPbWaaSbaaWqaaiaaigdaaeqa
aSGaeyicI4Saam4Caaqab0GaeyyeIuoakmaabmaabaGaaGymaiabgk
HiTiabec8aWnaaDaaaleaacaWGPbWaaSbaaWqaaiaaigdaaeqaaaWc
baGaeyOeI0IaaGymaaaaaOGaayjkaiaawMcaamaabmaabaGaaGymai
abgkHiTiabec8aWnaaDaaaleaacaWGPbWaaSbaaWqaaiaaikdaaeqa
aaWcbaGaeyOeI0IaaGymaaaaaOGaayjkaiaawMcaaiabgEna0kaabo
gacaqGVbGaaeODamaabmaabaGaamysamaabmaabaGaeqyTdu2aaSba
aSqaaiaadQgaaeqaaOGaeyizImQaamiDaiabgkHiTiaad2gadaWgaa
WcbaGaamyAamaaBaaameaacaaIXaaabeaaaSqabaGccqGHRaWkceWG
KbGbaGaadaWgaaWcbaGaamyAamaaBaaameaacaaIXaaabeaaliaaiY
cacaWGQbaabeaaaOGaayjkaiaawMcaaiaaiYcacaWGjbWaaeWaaeaa
cqaH1oqzdaWgaaWcbaGaamyAamaaBaaameaacaaIYaaabeaaaSqaba
GccqGHKjYOcaWG0bGaeyOeI0IaamyBamaaBaaaleaacaWGPbWaaSba
aWqaaiaaikdaaeqaaaWcbeaaaOGaayjkaiaawMcaaaGaayjkaiaawM
caaiaai6caaaa@91B8@
Pour commencer, considérons
E
1
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWGfbWaaS
baaSqaaiaaigdaaeqaaaaa@39A2@
et
E
2
.
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWGfbWaaS
baaSqaaiaaikdaaeqaaOGaaiOlaaaa@3A5F@
Notons que, à part i) le
fait que les indices de sommation
i
1
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWGPbWaaS
baaSqaaiaaigdaaeqaaaaa@39C6@
et
i
2
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWGPbWaaS
baaSqaaiaaikdaaeqaaaaa@39C7@
s’étendent sur
s
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWGZbaaaa@38E9@
au lieu du complément de
s
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWGZbaaaa@38E9@
dans
U
,
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWGvbGaai
ilaaaa@397B@
ii) la présence des
facteurs
(
1
−
π
i
−
1
)
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaadaqadaqaai
aaigdacqGHsislcqaHapaCdaqhaaWcbaGaamyAaaqaaiabgkHiTiaa
igdaaaaakiaawIcacaGLPaaaaaa@3FAC@
et iii) le fait que les
w
i
,
j
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWG3bWaaS
baaSqaaiaadMgacaaISaGaamOAaaqabaaaaa@3BAC@
et les
d
i
,
j
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWGKbWaaS
baaSqaaiaadMgacaaISaGaamOAaaqabaaaaa@3B99@
sont remplacés par leurs
équivalents pondérés selon le plan de sondage
w
˜
i
,
j
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaaceWG3bGbaG
aadaWgaaWcbaGaamyAaiaaiYcacaWGQbaabeaaaaa@3BBB@
et
d
˜
i
,
j
,
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaaceWGKbGbaG
aadaWgaaWcbaGaamyAaiaaiYcacaWGQbaabeaakiaacYcaaaa@3C62@
E
1
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWGfbWaaS
baaSqaaiaaigdaaeqaaaaa@39A2@
et
E
2
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWGfbWaaS
baaSqaaiaaikdaaeqaaaaa@39A3@
sont semblables à
D
1
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWGebWaaS
baaSqaaiaaigdaaeqaaaaa@39A1@
et
D
2
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWGebWaaS
baaSqaaiaaikdaaeqaaaaa@39A2@
provenant de
var
(
F
^
*
(
t
)
−
F
N
(
t
)
)
,
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaqG2bGaae
yyaiaabkhadaqadaqaaiqadAeagaqcamaaCaaaleqabaGaaGOkaaaa
kiaaygW7daqadaqaaiaadshaaiaawIcacaGLPaaacqGHsislcaWGgb
WaaSbaaSqaaiaad6eaaeqaaOWaaeWaaeaacaWG0baacaGLOaGaayzk
aaaacaGLOaGaayzkaaGaaiilaaaa@4811@
respectivement. L’adaptation
des preuves qui mènent aux développements asymptotiques pour
D
1
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWGebWaaS
baaSqaaiaaigdaaeqaaaaa@39A1@
et
D
2
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWGebWaaS
baaSqaaiaaikdaaeqaaaaa@39A2@
montre donc que
E
1
=
1
n
(
N
−
n
N
)
2
∫
a
b
[
G
(
t
−
m
(
x
)
|
x
)
−
G
2
(
t
−
m
(
x
)
|
x
)
]
[
1
−
π
−
1
(
x
)
]
2
h
s
(
x
)
d
x
+
o
(
n
−
1
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaafaqaaeqaca
aabaGaamyramaaBaaaleaacaaIXaaabeaaaOqaaiaai2dadaWcaaqa
aiaaigdaaeaacaWGUbaaamaabmaabaWaaSaaaeaacaWGobGaeyOeI0
IaamOBaaqaaiaad6eaaaaacaGLOaGaayzkaaWaaWbaaSqabeaacaaI
YaaaaOWaa8qmaeqaleaacaWGHbaabaGaamOyaaqdcqGHRiI8aOWaam
WaaeaacaWGhbWaaeWaaeaadaabcaqaaiaadshacqGHsislcaWGTbWa
aeWaaeaacaWG4baacaGLOaGaayzkaaGaaGPaVdGaayjcSdGaaGPaVl
aadIhaaiaawIcacaGLPaaacqGHsislcaWGhbWaaWbaaSqabeaacaaI
YaaaaOWaaeWaaeaadaabcaqaaiaadshacqGHsislcaWGTbWaaeWaae
aacaWG4baacaGLOaGaayzkaaGaaGPaVdGaayjcSdGaaGPaVlaadIha
aiaawIcacaGLPaaaaiaawUfacaGLDbaadaWadaqaaiaaigdacqGHsi
slcqaHapaCdaahaaWcbeqaaiabgkHiTiaaigdaaaGcdaqadaqaaiaa
dIhaaiaawIcacaGLPaaaaiaawUfacaGLDbaadaahaaWcbeqaaiaaik
daaaGccaWGObWaaSbaaSqaaiaadohaaeqaaOWaaeWaaeaacaWG4baa
caGLOaGaayzkaaGaamizaiaadIhacqGHRaWkcaWGVbWaaeWaaeaaca
WGUbWaaWbaaSqabeaacqGHsislcaaIXaaaaaGccaGLOaGaayzkaaaa
aaaa@7C40@
et que
E
2
=
o
(
λ
5
+
n
−
1
)
.
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWGfbWaaS
baaSqaaiaaikdaaeqaaOGaaGypaiaad+gadaqadaqaaiabeU7aSnaa
CaaaleqabaGaaGynaaaakiabgUcaRiaad6gadaahaaWcbeqaaiabgk
HiTiaaigdaaaaakiaawIcacaGLPaaacaaIUaaaaa@4406@
Comme pour
E
3
,
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWGfbWaaS
baaSqaaiaaiodaaeqaaOGaaiilaaaa@3A5E@
on constate immédiatement que
E
3
=
E
1
+
o
(
n
−
1
)
,
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWGfbWaaS
baaSqaaiaaiodaaeqaaOGaaGypaiaadweadaWgaaWcbaGaaGymaaqa
baGccqGHRaWkcaWGVbWaaeWaaeaacaWGUbWaaWbaaSqabeaacqGHsi
slcaaIXaaaaaGccaGLOaGaayzkaaGaaGilaaaa@4316@
tandis que, pour traiter
E
4
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWGfbWaaS
baaSqaaiaaisdaaeqaaaaa@39A5@
et
E
5
,
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWGfbWaaS
baaSqaaiaaiwdaaeqaaOGaaiilaaaa@3A60@
on a besoin des développements
asymptotiques pour
cov
(
I
(
ε
j
≤
t
−
m
i
1
+
d
˜
i
1
,
j
)
,
I
(
ε
i
2
≤
t
−
m
i
2
)
)
(
A
.21
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaqGJbGaae
4BaiaabAhadaqadaqaaiaadMeadaqadaqaaiabew7aLnaaBaaaleaa
caWGQbaabeaakiabgsMiJkaadshacqGHsislcaWGTbWaaSbaaSqaai
aadMgadaWgaaadbaGaaGymaaqabaaaleqaaOGaey4kaSIabmizayaa
iaWaaSbaaSqaaiaadMgadaWgaaadbaGaaGymaaqabaWccaaISaGaam
OAaaqabaaakiaawIcacaGLPaaacaaISaGaamysamaabmaabaGaeqyT
du2aaSbaaSqaaiaadMgadaWgaaadbaGaaGOmaaqabaaaleqaaOGaey
izImQaamiDaiabgkHiTiaad2gadaWgaaWcbaGaamyAamaaBaaameaa
caaIYaaabeaaaSqabaaakiaawIcacaGLPaaaaiaawIcacaGLPaaaca
aMf8UaaGzbVlaaywW7caaMf8UaaGzbVlaacIcacaGGbbGaaiOlaiaa
ikdacaaIXaGaaiykaaaa@6725@
pour le cas où
j
=
i
2
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWGQbGaaG
ypaiaadMgadaWgaaWcbaGaaGOmaaqabaaaaa@3B7D@
et celui où
j
≠
i
2
.
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWGQbGaey
iyIKRaamyAamaaBaaaleaacaaIYaaabeaakiaac6caaaa@3D39@
Dans le premier cas, nous
pouvons faire appel à des arguments similaires à ceux utilisés pour prouver
(A.9) et (A.10), ce qui donne
cov
(
I
(
ε
j
≤
t
−
m
i
1
+
d
˜
i
1
,
j
)
,
I
(
ε
j
≤
t
−
m
j
)
)
=
G
(
t
−
m
i
1
∧
t
−
m
j
|
x
j
)
−
G
(
t
−
m
i
1
|
x
j
)
G
(
t
−
m
j
|
x
j
)
+
O
(
λ
2
+
(
n
λ
)
−
1
/
2
)
.
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaafaqaaeGaba
aabaGaae4yaiaab+gacaqG2bWaaeWaaeaacaWGjbWaaeWaaeaacqaH
1oqzdaWgaaWcbaGaamOAaaqabaGccqGHKjYOcaWG0bGaeyOeI0Iaam
yBamaaBaaaleaacaWGPbWaaSbaaWqaaiaaigdaaeqaaaWcbeaakiab
gUcaRiqadsgagaacamaaBaaaleaacaWGPbWaaSbaaWqaaiaaigdaae
qaaSGaaGilaiaadQgaaeqaaaGccaGLOaGaayzkaaGaaGilaiaadMea
daqadaqaaiabew7aLnaaBaaaleaacaWGQbaabeaakiabgsMiJkaads
hacqGHsislcaWGTbWaaSbaaSqaaiaadQgaaeqaaaGccaGLOaGaayzk
aaaacaGLOaGaayzkaaaabaGaaGjbVlaaysW7caaMe8UaaGjbVlaays
W7caaMe8UaaGjbVlaaysW7caaMe8UaaGypaiaadEeadaqadaqaamaa
eiaabaGaamiDaiabgkHiTiaad2gadaWgaaWcbaGaamyAamaaBaaame
aacaaIXaaabeaaaSqabaGccqGHNis2caWG0bGaeyOeI0IaamyBamaa
BaaaleaacaWGQbaabeaakiaaykW7aiaawIa7aiaaykW7caWG4bWaaS
baaSqaaiaadQgaaeqaaaGccaGLOaGaayzkaaGaeyOeI0Iaam4ramaa
bmaabaWaaqGaaeaacaWG0bGaeyOeI0IaamyBamaaBaaaleaacaWGPb
WaaSbaaWqaaiaaigdaaeqaaaWcbeaakiaaykW7aiaawIa7aiaaykW7
caWG4bWaaSbaaSqaaiaadQgaaeqaaaGccaGLOaGaayzkaaGaam4ram
aabmaabaWaaqGaaeaacaWG0bGaeyOeI0IaamyBamaaBaaaleaacaWG
QbaabeaakiaaykW7aiaawIa7aiaaykW7caWG4bWaaSbaaSqaaiaadQ
gaaeqaaaGccaGLOaGaayzkaaGaey4kaSIaam4tamaabmaabaGaeq4U
dW2aaWbaaSqabeaacaaIYaaaaOGaey4kaSYaaeWaaeaacaWGUbGaeq
4UdWgacaGLOaGaayzkaaWaaWbaaSqabeaacqGHsisldaWcgaqaaiaa
igdaaeaacaaIYaaaaaaaaOGaayjkaiaawMcaaiaai6caaaaaaa@A637@
Par contre, quand
j
≠
i
2
,
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWGQbGaey
iyIKRaamyAamaaBaaaleaacaaIYaaabeaakiaacYcaaaa@3D37@
la covariance dans (A.21)
diffère de zéro uniquement si
|
x
j
−
x
i
2
|
≤
λ
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaadaabdaqaai
aaykW7caWG4bWaaSbaaSqaaiaadQgaaeqaaOGaeyOeI0IaamiEamaa
BaaaleaacaWGPbWaaSbaaWqaaiaaikdaaeqaaaWcbeaaaOGaay5bSl
aawIa7aiabgsMiJkabeU7aSbaa@462B@
ou
|
x
i
1
−
x
i
2
|
≤
λ
,
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaadaabdaqaai
aaykW7caWG4bWaaSbaaSqaaiaadMgadaWgaaadbaGaaGymaaqabaaa
leqaaOGaeyOeI0IaamiEamaaBaaaleaacaWGPbWaaSbaaWqaaiaaik
daaeqaaaWcbeaaaOGaay5bSlaawIa7aiabgsMiJkabeU7aSjaacYca
aaa@47CD@
et en adaptant (A.12), on peut
montrer que
E
(
I
(
ε
j
≤
t
−
m
i
1
+
d
˜
i
1
,
j
)
I
(
ε
i
2
≤
t
−
m
i
2
)
)
=
E
(
E
(
I
(
ε
j
≤
a
˜
i
1
,
j
,
i
2
+
b
˜
i
1
,
j
,
i
2
ε
i
2
)
I
(
ε
i
2
≤
t
−
m
i
2
)
|
ε
k
,
k
≠
i
,
j
)
)
=
E
(
∫
−
∞
t
−
m
i
2
G
(
a
˜
i
1
,
j
,
i
2
+
b
˜
i
1
,
j
,
i
2
ε
|
x
j
)
d
G
(
ε
|
x
i
2
)
)
=
G
(
t
−
m
i
1
|
x
j
)
G
(
t
−
m
i
2
|
x
i
2
)
+
G
(
t
−
m
i
2
|
x
i
2
)
G
(
1
,
0
)
(
t
−
m
i
1
|
x
j
)
E
(
d
i
1
,
j
)
+
G
(
1
,
0
)
(
t
−
m
i
1
|
x
j
)
b
˜
i
1
,
j
,
i
2
γ
i
2
,
i
2
+
1
2
G
(
t
−
m
i
2
|
x
i
2
)
G
(
2
,
0
)
(
t
−
m
i
1
|
x
j
)
E
(
d
i
1
,
j
2
)
+
o
i
1
,
i
2
,
j
(
λ
4
+
(
n
λ
)
−
1
)
,
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaafaqaaeGbba
aaaeaacaWGfbWaaeWaaeaacaWGjbWaaeWaaeaacqaH1oqzdaWgaaWc
baGaamOAaaqabaGccqGHKjYOcaWG0bGaeyOeI0IaamyBamaaBaaale
aacaWGPbWaaSbaaeaacaaIXaaabeaaaeqaaOGaey4kaSIabmizayaa
iaWaaSbaaSqaaiaadMgadaWgaaadbaGaaGymaaqabaWccaaISaGaam
OAaaqabaaakiaawIcacaGLPaaacaWGjbWaaeWaaeaacqaH1oqzdaWg
aaWcbaGaamyAamaaBaaameaacaaIYaaabeaaaSqabaGccqGHKjYOca
WG0bGaeyOeI0IaamyBamaaBaaaleaacaWGPbWaaSbaaWqaaiaaikda
aeqaaaWcbeaaaOGaayjkaiaawMcaaaGaayjkaiaawMcaaaqaaiaays
W7caaMe8UaaGjbVlaaysW7caaMe8UaaGypaiaadweadaqadaqaaiaa
dweadaqadaqaamaaeiaabaGaamysamaabmaabaGaeqyTdu2aaSbaaS
qaaiaadQgaaeqaaOGaeyizImQabmyyayaaiaWaaSbaaSqaaiaadMga
daWgaaadbaGaaGymaaqabaWccaaISaGaamOAaiaaiYcacaWGPbWaaS
baaWqaaiaaikdaaeqaaaWcbeaakiabgUcaRmaaGaaabaGaamOyaaGa
ay5adaWaaSbaaSqaaiaadMgadaWgaaadbaGaaGymaaqabaWccaaISa
GaamOAaiaaiYcacaWGPbWaaSbaaWqaaiaaikdaaeqaaaWcbeaakiab
ew7aLnaaBaaaleaacaWGPbWaaSbaaWqaaiaaikdaaeqaaaWcbeaaaO
GaayjkaiaawMcaaiaadMeadaqadaqaaiabew7aLnaaBaaaleaacaWG
PbWaaSbaaWqaaiaaikdaaeqaaaWcbeaakiabgsMiJkaadshacqGHsi
slcaWGTbWaaSbaaSqaaiaadMgadaWgaaadbaGaaGOmaaqabaaaleqa
aaGccaGLOaGaayzkaaGaaGPaVdGaayjcSdGaaGPaVlabew7aLnaaBa
aaleaacaWGRbaabeaakiaaiYcacaWGRbGaeyiyIKRaamyAaiaaiYca
caWGQbaacaGLOaGaayzkaaaacaGLOaGaayzkaaaabaGaaGjbVlaays
W7caaMe8UaaGjbVlaaysW7caaI9aGaamyramaabmaabaWaa8qmaeqa
leaacqGHsislcqGHEisPaeaacaWG0bGaeyOeI0IaamyBamaaBaaame
aacaWGPbWaaSbaaeaacaaIYaaabeaaaeqaaaqdcqGHRiI8aOGaam4r
amaabmaabaGabmyyayaaiaWaaSbaaSqaaiaadMgadaWgaaadbaGaaG
ymaaqabaWccaaISaGaamOAaiaaiYcacaWGPbWaaSbaaWqaaiaaikda
aeqaaaWcbeaakiabgUcaRmaaeiaabaWaaacaaeaacaWGIbaacaGLdm
aadaWgaaWcbaGaamyAamaaBaaameaacaaIXaaabeaaliaaiYcacaWG
QbGaaGilaiaadMgadaWgaaadbaGaaGOmaaqabaaaleqaaOGaeqyTdu
MaaGPaVdGaayjcSdGaaGPaVlaadIhadaWgaaWcbaGaamOAaaqabaaa
kiaawIcacaGLPaaacaWGKbGaam4ramaabmaabaWaaqGaaeaacqaH1o
qzcaaMc8oacaGLiWoacaWG4bWaaSbaaSqaaiaadMgadaWgaaadbaGa
aGOmaaqabaaaleqaaaGccaGLOaGaayzkaaaacaGLOaGaayzkaaaaba
GaaGjbVlaaysW7caaMe8UaaGjbVlaaysW7caaI9aGaam4ramaabmaa
baWaaqGaaeaacaWG0bGaeyOeI0IaamyBamaaBaaaleaacaWGPbWaaS
baaWqaaiaaigdaaeqaaaWcbeaakiaaykW7aiaawIa7aiaaykW7caWG
4bWaaSbaaSqaaiaadQgaaeqaaaGccaGLOaGaayzkaaGaam4ramaabm
aabaWaaqGaaeaacaWG0bGaeyOeI0IaamyBamaaBaaaleaacaWGPbWa
aSbaaWqaaiaaikdaaeqaaaWcbeaakiaaykW7aiaawIa7aiaaykW7ca
WG4bWaaSbaaSqaaiaadMgadaWgaaadbaGaaGOmaaqabaaaleqaaaGc
caGLOaGaayzkaaGaey4kaSIaam4ramaabmaabaWaaqGaaeaacaWG0b
GaeyOeI0IaamyBamaaBaaaleaacaWGPbWaaSbaaWqaaiaaikdaaeqa
aaWcbeaakiaaykW7aiaawIa7aiaaykW7caWG4bWaaSbaaSqaaiaadM
gadaWgaaadbaGaaGOmaaqabaaaleqaaaGccaGLOaGaayzkaaGaam4r
amaaCaaaleqabaWaaeWaaeaacaaIXaGaaiilaiaaicdaaiaawIcaca
GLPaaaaaGcdaqadaqaamaaeiaabaGaamiDaiabgkHiTiaad2gadaWg
aaWcbaGaamyAamaaBaaameaacaaIXaaabeaaaSqabaGccaaMc8oaca
GLiWoacaaMc8UaamiEamaaBaaaleaacaWGQbaabeaaaOGaayjkaiaa
wMcaaiaadweadaqadaqaaiaadsgadaWgaaWcbaGaamyAamaaBaaame
aacaaIXaaabeaaliaaiYcacaWGQbaabeaaaOGaayjkaiaawMcaaaqa
aiaaysW7caaMe8UaaGjbVlaaysW7caaMe8UaaGjbVlaaysW7cqGHRa
WkcaWGhbWaaWbaaSqabeaadaqadaqaaiaaigdacaGGSaGaaGimaaGa
ayjkaiaawMcaaaaakmaabmaabaWaaqGaaeaacaWG0bGaeyOeI0Iaam
yBamaaBaaaleaacaWGPbWaaSbaaWqaaiaaigdaaeqaaaWcbeaakiaa
ykW7aiaawIa7aiaaykW7caWG4bWaaSbaaSqaaiaadQgaaeqaaaGcca
GLOaGaayzkaaWaaacaaeaacaWGIbaacaGLdmaadaWgaaWcbaGaamyA
amaaBaaameaacaaIXaaabeaaliaaiYcacaWGQbGaaGilaiaadMgada
WgaaadbaGaaGOmaaqabaaaleqaaOGaeq4SdC2aaSbaaSqaaiaadMga
daWgaaadbaGaaGOmaaqabaWccaaISaGaamyAamaaBaaameaacaaIYa
aabeaaaSqabaGccqGHRaWkdaWcaaqaaiaaigdaaeaacaaIYaaaaiaa
dEeadaqadaqaamaaeiaabaGaamiDaiabgkHiTiaad2gadaWgaaWcba
GaamyAamaaBaaameaacaaIYaaabeaaaSqabaGccaaMc8oacaGLiWoa
caaMc8UaamiEamaaBaaaleaacaWGPbWaaSbaaWqaaiaaikdaaeqaaa
WcbeaaaOGaayjkaiaawMcaaiaadEeadaahaaWcbeqaamaabmaabaGa
aGOmaiaacYcacaaIWaaacaGLOaGaayzkaaaaaOWaaeWaaeaadaabca
qaaiaadshacqGHsislcaWGTbWaaSbaaSqaaiaadMgadaWgaaadbaGa
aGymaaqabaaaleqaaOGaaGPaVdGaayjcSdGaaGPaVlaadIhadaWgaa
WcbaGaamOAaaqabaaakiaawIcacaGLPaaacaWGfbWaaeWaaeaacaWG
KbWaa0baaSqaaiaadMgadaWgaaadbaGaaGymaaqabaWccaaISaGaam
OAaaqaaiaaikdaaaaakiaawIcacaGLPaaaaeaacaaMe8UaaGjbVlaa
ysW7caaMe8UaaGjbVlaaysW7caaMe8Uaey4kaSIaam4BamaaBaaale
aacaWGPbWaaSbaaWqaaiaaigdaaeqaaSGaaGilaiaadMgadaWgaaad
baGaaGOmaaqabaWccaaISaGaamOAaaqabaGcdaqadaqaaiabeU7aSn
aaCaaaleqabaGaaGinaaaakiabgUcaRmaabmaabaGaamOBaiabeU7a
SbGaayjkaiaawMcaamaaCaaaleqabaGaeyOeI0IaaGymaaaaaOGaay
jkaiaawMcaaiaaiYcaaaaaaa@993C@
où
a
˜
i
,
j
,
k
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaaceWGHbGbaG
aadaWgaaWcbaGaamyAaiaaiYcacaWGQbGaaGilaiaadUgaaeqaaaaa
@3D4B@
et
b
˜
i
,
j
,
k
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaadaaiaaqaai
aadkgaaiaawoWaamaaBaaaleaacaWGPbGaaGilaiaadQgacaaISaGa
am4Aaaqabaaaaa@3DFF@
sont les équivalents pondérés
selon le plan de sondage de
a
i
,
j
,
k
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWGHbWaaS
baaSqaaiaadMgacaaISaGaamOAaiaaiYcacaWGRbaabeaaaaa@3D3C@
et
b
i
,
j
,
k
,
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWGIbWaaS
baaSqaaiaadMgacaaISaGaamOAaiaaiYcacaWGRbaabeaakiaacYca
aaa@3DF7@
respectivement. En adaptant
également (A.4) pour tenir compte des poids de sondage, on constate que
cov
(
I
(
ε
j
≤
t
−
m
i
1
+
d
˜
i
1
,
j
)
,
I
(
ε
i
2
≤
t
−
m
i
2
)
)
=
G
(
1
,
0
)
(
t
−
m
i
1
|
x
j
)
b
˜
i
1
,
j
,
i
2
γ
i
2
,
i
2
+
o
i
1
,
i
2
,
j
(
λ
4
+
(
n
λ
)
−
1
)
=
G
(
1
,
0
)
(
t
−
m
i
|
x
j
)
(
w
˜
j
,
i
2
−
w
˜
i
1
,
i
2
)
γ
i
2
,
i
2
+
o
i
1
,
i
2
,
j
(
λ
4
+
(
n
λ
)
−
1
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaafaqaaeGaca
aabaGaae4yaiaab+gacaqG2bWaaeWaaeaacaWGjbWaaeWaaeaacqaH
1oqzdaWgaaWcbaGaamOAaaqabaGccqGHKjYOcaWG0bGaeyOeI0Iaam
yBamaaBaaaleaacaWGPbWaaSbaaWqaaiaaigdaaeqaaaWcbeaakiab
gUcaRiqadsgagaacamaaBaaaleaacaWGPbWaaSbaaWqaaiaaigdaae
qaaSGaaGilaiaadQgaaeqaaaGccaGLOaGaayzkaaGaaGilaiaadMea
daqadaqaaiabew7aLnaaBaaaleaacaWGPbWaaSbaaWqaaiaaikdaae
qaaaWcbeaakiabgsMiJkaadshacqGHsislcaWGTbWaaSbaaSqaaiaa
dMgadaWgaaadbaGaaGOmaaqabaaaleqaaaGccaGLOaGaayzkaaaaca
GLOaGaayzkaaaabaGaaGypaiaadEeadaahaaWcbeqaamaabmaabaGa
aGymaiaacYcacaaIWaaacaGLOaGaayzkaaaaaOWaaeWaaeaadaabca
qaaiaadshacqGHsislcaWGTbWaaSbaaSqaaiaadMgadaWgaaadbaGa
aGymaaqabaaaleqaaOGaaGPaVdGaayjcSdGaaGPaVlaadIhadaWgaa
WcbaGaamOAaaqabaaakiaawIcacaGLPaaadaaiaaqaaiaadkgaaiaa
woWaamaaBaaaleaacaWGPbWaaSbaaWqaaiaaigdaaeqaaSGaaGilai
aadQgacaaISaGaamyAamaaBaaameaacaaIYaaabeaaaSqabaGccqaH
ZoWzdaWgaaWcbaGaamyAamaaBaaameaacaaIYaaabeaaliaaiYcaca
WGPbWaaSbaaWqaaiaaikdaaeqaaaWcbeaakiabgUcaRiaad+gadaWg
aaWcbaGaamyAamaaBaaameaacaaIXaaabeaaliaaiYcacaWGPbWaaS
baaWqaaiaaikdaaeqaaSGaaGilaiaadQgaaeqaaOWaaeWaaeaacqaH
7oaBdaahaaWcbeqaaiaaisdaaaGccqGHRaWkdaqadaqaaiaad6gacq
aH7oaBaiaawIcacaGLPaaadaahaaWcbeqaaiabgkHiTiaaigdaaaaa
kiaawIcacaGLPaaaaeaaaeaacaaI9aGaam4ramaaCaaaleqabaWaae
WaaeaacaaIXaGaaiilaiaaicdaaiaawIcacaGLPaaaaaGcdaqadaqa
amaaeiaabaGaamiDaiabgkHiTiaad2gadaWgaaWcbaGaamyAaaqaba
GccaaMc8oacaGLiWoacaaMc8UaamiEamaaBaaaleaacaWGQbaabeaa
aOGaayjkaiaawMcaamaabmaabaGabm4DayaaiaWaaSbaaSqaaiaadQ
gacaaISaGaamyAamaaBaaameaacaaIYaaabeaaaSqabaGccqGHsisl
ceWG3bGbaGaadaWgaaWcbaGaamyAamaaBaaameaacaaIXaaabeaali
aaiYcacaWGPbWaaSbaaWqaaiaaikdaaeqaaaWcbeaaaOGaayjkaiaa
wMcaaiabeo7aNnaaBaaaleaacaWGPbWaaSbaaWqaaiaaikdaaeqaaS
GaaGilaiaadMgadaWgaaadbaGaaGOmaaqabaaaleqaaOGaey4kaSIa
am4BamaaBaaaleaacaWGPbWaaSbaaWqaaiaaigdaaeqaaSGaaGilai
aadMgadaWgaaadbaGaaGOmaaqabaWccaaISaGaamOAaaqabaGcdaqa
daqaaiabeU7aSnaaCaaaleqabaGaaGinaaaakiabgUcaRmaabmaaba
GaamOBaiabeU7aSbGaayjkaiaawMcaamaaCaaaleqabaGaeyOeI0Ia
aGymaaaaaOGaayjkaiaawMcaaaaaaaa@C7ED@
de sorte que (voir les étapes qui mènent aux
développements asymptotiques des termes
D
1
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWGebWaaS
baaSqaaiaaigdaaeqaaaaa@39A1@
et
D
2
MathType@MTEF@5@5@+=
feaagKart1ev2aqatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWGebWaaS
baaSqaaiaaikdaaeqaaaaa@39A2@
dans la variance de l’estimateur
en deux étapes fondé sur le modèle)
E
4
=
E
1
+
o
(
n
−
1
)
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWGfbWaaS
baaSqaaiaaisdaaeqaaOGaaGypaiaadweadaWgaaWcbaGaaGymaaqa
baGccqGHRaWkcaWGVbWaaeWaaeaacaWGUbWaaWbaaSqabeaacqGHsi
slcaaIXaaaaaGccaGLOaGaayzkaaaaaa@4261@
et
E
5
=
o
(
λ
5
+
n
−
1
)
.
MathType@MTEF@5@5@+=
feaagKart1ev2aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn
hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr
4rNCHbGeaGqiFu0Je9sqqrpepC0xbbL8F4rqqrpgpeea0xe9Lqpe0x
e9q8qqvqFr0dXdbrVc=b0P0xb9peee0hXddrpe0=1qpeea0=yrVue9
Fve9Fve8meaabaqaciGacaGaaeqabaWaaeaaeaaakeaacaWGfbWaaS
baaSqaaiaaiwdaaeqaaOGaaGypaiaad+gadaqadaqaaiabeU7aSnaa
CaaaleqabaGaaGynaaaakiabgUcaRiaad6gadaahaaWcbeqaaiabgk
HiTiaaigdaaaaakiaawIcacaGLPaaacaaIUaaaaa@4409@
Cela achève la preuve de (A.20) et
donc (A.19) s’ensuit.
Bibliographie
Breidt, F.J., et Opsomer, J.D. (2000). Local polynomial regression estimators in survey sampling. The Annals
Statistics , 28(4), 1026-1053.
Chambers, R.L., et Clark,
R. (2012). An Introduction to Model-Based Survey Sampling with Applications ,
Oxford Statistical Science Series 37.
Chambers, R.L., et Dunstan, R. (1986). Estimating distribution functions from survey data. Biometrika ,
73(3), 597-604.
Chambers, R.L., Dorfman,
A.H. et Wehrly, T.E. (1993). Bias robust estimation in finite populations using
non-parametric calibration. Journal of the American Statistical Association ,
88(421), 268-277.
Chen, J., et Wu, C. (2002). Estimation
of distribution function and quantiles using the model-calibrated pseudo
empirical likelihood method. Statistica Sinica , 12, 1223-1239.
Dorfman, A.H., et Hall,
P. (1993). Estimators of the finite population distribution function using
nonparametric regression. The Annals of Statistics , 21(3),
1452-1475.
Fan, J., et Gijbels, I.
(1992). Variable bandwidth and local linear regression smoothers. The Annals
of Statistics , 20(4), 2008-2036.
Hansen, B.E. (2008).
Uniform convergence rates for kernel estimation with dependent data. Econometric
Theory , 24, 726-748.
Johnson, A.A., Breidt,
F.J. et Opsomer, J.D. (2008). Estimating distribution functions from survey
data using nonparametric regression. Journal of Statistical Theory and
Practice , 2(3), 419-431.
Kuo, L. (1988). Classical
and prediction approaches to estimating distribution functions from survey
data. Dans les Proceedings of the Survey Research Methods Section, American Statistical Association, Alexandria, VA, 280-285.
Montanari, G.E., et Ranalli, M.G. (2005). Nonparametric model calibration estimation in survey sampling. Journal
of the American Statistical Association , 100(472), 1429-1442.
Rao, J.N.K., Kovar, J.G. et
Mantel, H.J. (1990). On estimating distribution functions and quantiles from
survey data using auxiliary information. Biometrika , 77(2), 365-375.
Rueda, M., Martínez, S., Martínez, H. et Arcos, A. (2007). Estimation of the distribution function with
calibration methods. Journal of Statistical Planning and Inference ,
137(2), 435-448.
Rueda, M.,
Sànchez-Borrego, I., Arcos, A. et Martínez, S. (2010). Model-calibration
estimation of the distribution function using nonparametric regression. Metrika ,
71(1), 33-44.
Särndal, C.-E., Swensson,
B. et Wretman, J. (1992). Model Assisted Survey Sampling , New York :
Springer.
Wang, J.C., et Opsomer,
J.D. (2011). On asymptotic normality and variance estimation for
nondifferentiable survey estimators. Biometrika , 98(1), 91-106.
Wu, C. (2003). Optimal
calibration estimators in survey sampling. Biometrika , 90(4), 937-951.
Wu, C., et Sitter, R.R. (2001). A
model-calibration approach to using complete auxiliary information from survey
data. Journal of the American Statistical Association , 96(453), 185-193.
ISSN : 1712-5685
Politique de rédaction
Techniques d ’enquête publie des articles sur les divers aspects des méthodes statistiques qui intéressent un organisme statistique comme, par exemple, les problèmes de conception découlant de contraintes d’ordre pratique, l’utilisation de différentes sources de données et de méthodes de collecte, les erreurs dans les enquêtes, l’évaluation des enquêtes, la recherche sur les méthodes d’enquête, l’analyse des séries chronologiques, la désaisonnalisation, les études démographiques, l’intégration de données statistiques, les méthodes d’estimation et d’analyse de données et le développement de systèmes généralisés. Une importance particulière est accordée à l’élaboration et à l’évaluation de méthodes qui ont été utilisées pour la collecte de données ou appliquées à des données réelles. Tous les articles seront soumis à une critique, mais les auteurs demeurent responsables du contenu de leur texte et les opinions émises dans la revue ne sont pas nécessairement celles du comité de rédaction ni de Statistique Canada.
Présentation de textes pour la revue
Techniques d ’enquête est publiée en version électronique deux fois l’an. Les auteurs désirant faire paraître un article sont invités à le faire parvenir en français ou en anglais en format électronique et préférablement en Word au rédacteur en chef, (statcan.smj-rte.statcan@canada.ca , Statistique Canada, 150 Promenade du Pré Tunney, Ottawa, (Ontario), Canada, K1A 0T6). Pour les instructions sur le format, veuillez consulter les directives présentées dans la revue ou sur le site web (www.statcan.gc.ca/Techniquesdenquete).
Note de reconnaissance
Le succès du système statistique du Canada repose sur un partenariat bien établi entre Statistique Canada et la population, les entreprises, les administrations canadiennes et les autres organismes. Sans cette collaboration et cette bonne volonté, il serait impossible de produire des statistiques précises et actuelles.
Normes de service à la clientèle
Statistique Canada s'engage à fournir à ses clients des services rapides, fiables et courtois. À cet égard, notre organisme s'est doté de normes de service à la clientèle qui doivent être observées par les employés lorsqu'ils offrent des services à la clientèle.
Droit d'auteur
Publication autorisée par le ministre responsable de Statistique Canada.
© Ministre de l'Industrie, 2016
L'utilisation de la présente publication est assujettie aux modalités de l'Entente de licence ouverte de Statistique Canada .
N° 12-001-X au catalogue
Périodicité : Semi-annuel
Ottawa
Date de modification :
2016-06-22