Table C.1
Goodness of fit of models that predict speed of closure of trajectories of transition to retirement, Canada, 1998 to 2001

Warning View the most recent version.

Archived Content

Information identified as archived is provided for reference, research or recordkeeping purposes. It is not subject to the Government of Canada Web Standards and has not been altered or updated since it was archived. Please "contact us" to request a format other than those available.

  Chapter 15,
self-employed versus employees		 Chapter 16,
public sector versus private sector
Type of model clogit clogit
Number of response levels 4 4
Weight variable NormWeight1 NormWeight
Number of observations used 1337 1337
Sum of weights used 1337 1337
Response frequencies
Closed Q1 to Q3 345 345
Closed Q4 to Q9 170 170
Closed Q10 to Q15 116 116
Unclosed 706 706
Testing the global null hypothesis: beta=0
-2 Log L2 for beta = 0 3118.71 3118.71
-2 Log L for model 2515.35 2466.33
Chi-Square 603.36 652.38
Degrees of freedom 25.00 28.00
Association of predicted probabilities and observed responses
Percent concordant 77.30 77.80
Percent discordant 22.50 22.00
Percent tied 0.20 0.20
Tau-a 0.35 0.35
1. The original SLID general longitudinal weight for each respondent is divided by the average of all weights in the sample, to provide an approximate adjustment of estimated standard errors of parameters, to take into account complex survey design.
2. Minus 2 times the log-likelihood statistic.
Source: Statistics Canada, Survey of Labour and Income Dynamics, longitudinal file.
Table source: Statistics Canada, 2008, New Frontiers of Research on Retirement: Technical Annex, catalogue number 75-515-XWE.