Weighting and estimation

Skip to main content
Skip to footer

Language selection

Français

Search and menus

Search and menus

Search

Skip to filters. View results.

Results

All (80)

All (80) (0 to 10 of 80 results)

1. A Model-based Disaggregation Method for Estimation of Adult Competency Archived
Articles and reports: 11-522-X202200100003
Description: Estimation at fine levels of aggregation is necessary to better describe society. Small area estimation model-based approaches that combine sparse survey data with rich data from auxiliary sources have been proven useful to improve the reliability of estimates for small domains. Considered here is a scenario where small area model-based estimates, produced at a given aggregation level, needed to be disaggregated to better describe the social structure at finer levels. For this scenario, an allocation method was developed to implement the disaggregation, overcoming challenges associated with data availability and model development at such fine levels. The method is applied to adult literacy and numeracy estimation at the county-by-group-level, using data from the U.S. Program for the International Assessment of Adult Competencies. In this application the groups are defined in terms of age or education, but the method could be applied to estimation of other equity-deserving groups.
Release date: 2024-03-25
2. Measuring the number of food aid recipients Archived
Articles and reports: 11-522-X202200100013
Description: Respondents to typical household surveys tend to significantly underreport their potential use of food aid distributed by associations. This underreporting is most likely related to the social stigma felt by people experiencing great financial difficulty. As a result, survey estimates of the number of recipients of that aid are much lower than the direct counts from the associations. Those counts tend to overestimate due to double counting. Through its adapted protocol, the Enquête Aide alimentaire (EAA) collected in late 2021 in France at a sample of sites of food aid distribution associations, controls the biases that affect the other sources and determines to what extent this aid is used.
Release date: 2024-03-25
3. A method for estimating the effect of classification errors on statistics for two domains
Articles and reports: 12-001-X202300200002
Description: Being able to quantify the accuracy (bias, variance) of published output is crucial in official statistics. Output in official statistics is nearly always divided into subpopulations according to some classification variable, such as mean income by categories of educational level. Such output is also referred to as domain statistics. In the current paper, we limit ourselves to binary classification variables. In practice, misclassifications occur and these contribute to the bias and variance of domain statistics. Existing analytical and numerical methods to estimate this effect have two disadvantages. The first disadvantage is that they require that the misclassification probabilities are known beforehand and the second is that the bias and variance estimates are biased themselves. In the current paper we present a new method, a Gaussian mixture model estimated by an Expectation-Maximisation (EM) algorithm combined with a bootstrap, referred to as the EM bootstrap method. This new method does not require that the misclassification probabilities are known beforehand, although it is more efficient when a small audit sample is used that yields a starting value for the misclassification probabilities in the EM algorithm. We compared the performance of the new method with currently available numerical methods: the bootstrap method and the SIMEX method. Previous research has shown that for non-linear parameters the bootstrap outperforms the analytical expressions. For nearly all conditions tested, the bias and variance estimates that are obtained by the EM bootstrap method are closer to their true values than those obtained by the bootstrap and SIMEX methods. We end this paper by discussing the results and possible future extensions of the method.
Release date: 2024-01-03
4. Relative performance of methods based on model-assisted survey regression estimation: A simulation study
Articles and reports: 12-001-X202200100003
Description:
Use of auxiliary data to improve the efficiency of estimators of totals and means through model-assisted survey regression estimation has received considerable attention in recent years. Generalized regression (GREG) estimators, based on a working linear regression model, are currently used in establishment surveys at Statistics Canada and several other statistical agencies. GREG estimators use common survey weights for all study variables and calibrate to known population totals of auxiliary variables. Increasingly, many auxiliary variables are available, some of which may be extraneous. This leads to unstable GREG weights when all the available auxiliary variables, including interactions among categorical variables, are used in the working linear regression model. On the other hand, new machine learning methods, such as regression trees and lasso, automatically select significant auxiliary variables and lead to stable nonnegative weights and possible efficiency gains over GREG. In this paper, a simulation study, based on a real business survey sample data set treated as the target population, is conducted to study the relative performance of GREG, regression trees and lasso in terms of efficiency of the estimators and properties of associated regression weights. Both probability sampling and non-probability sampling scenarios are studied.

Release date: 2022-06-21
5. Two local diagnostics to evaluate the efficiency of the empirical best predictor under the Fay-Herriot model
Articles and reports: 12-001-X202100200001
Description:
The Fay-Herriot model is often used to produce small area estimates. These estimates are generally more efficient than standard direct estimates. In order to evaluate the efficiency gains obtained by small area estimation methods, model mean square error estimates are usually produced. However, these estimates do not reflect all the peculiarities of a given domain (or area) because model mean square errors integrate out the local effects. An alternative is to estimate the design mean square error of small area estimators, which is often more attractive from a user point of view. However, it is known that design mean square error estimates can be very unstable, especially for domains with few sampled units. In this paper, we propose two local diagnostics that aim to choose between the empirical best predictor and the direct estimator for a particular domain. We first find an interval for the local effect such that the best predictor is more efficient under the design than the direct estimator. Then, we consider two different approaches to assess whether it is plausible that the local effect falls in this interval. We evaluate our diagnostics using a simulation study. Our preliminary results indicate that our diagnostics are effective for choosing between the empirical best predictor and the direct estimator.
Release date: 2022-01-06
6. Reducing the response imbalance: Is the accuracy of the survey estimates improved? Archived
Articles and reports: 12-001-X201600214663
Description:
We present theoretical evidence that efforts during data collection to balance the survey response with respect to selected auxiliary variables will improve the chances for low nonresponse bias in the estimates that are ultimately produced by calibrated weighting. One of our results shows that the variance of the bias – measured here as the deviation of the calibration estimator from the (unrealized) full-sample unbiased estimator – decreases linearly as a function of the response imbalance that we assume measured and controlled continuously over the data collection period. An attractive prospect is thus a lower risk of bias if one can manage the data collection to get low imbalance. The theoretical results are validated in a simulation study with real data from an Estonian household survey.
Release date: 2016-12-20
7. Tests for evaluating nonresponse bias in surveys Archived
Articles and reports: 12-001-X201600214677
Description:
How do we tell whether weighting adjustments reduce nonresponse bias? If a variable is measured for everyone in the selected sample, then the design weights can be used to calculate an approximately unbiased estimate of the population mean or total for that variable. A second estimate of the population mean or total can be calculated using the survey respondents only, with weights that have been adjusted for nonresponse. If the two estimates disagree, then there is evidence that the weight adjustments may not have removed the nonresponse bias for that variable. In this paper we develop the theoretical properties of linearization and jackknife variance estimators for evaluating the bias of an estimated population mean or total by comparing estimates calculated from overlapping subsets of the same data with different sets of weights, when poststratification or inverse propensity weighting is used for the nonresponse adjustments to the weights. We provide sufficient conditions on the population, sample, and response mechanism for the variance estimators to be consistent, and demonstrate their small-sample properties through a simulation study.
Release date: 2016-12-20
8. One step or two? Calibration weighting from a complete list frame with nonresponse Archived
Articles and reports: 12-001-X201500114172
Description:
When a random sample drawn from a complete list frame suffers from unit nonresponse, calibration weighting to population totals can be used to remove nonresponse bias under either an assumed response (selection) or an assumed prediction (outcome) model. Calibration weighting in this way can not only provide double protection against nonresponse bias, it can also decrease variance. By employing a simple trick one can estimate the variance under the assumed prediction model and the mean squared error under the combination of an assumed response model and the probability-sampling mechanism simultaneously. Unfortunately, there is a practical limitation on what response model can be assumed when design weights are calibrated to population totals in a single step. In particular, the choice for the response function cannot always be logistic. That limitation does not hinder calibration weighting when performed in two steps: from the respondent sample to the full sample to remove the response bias and then from the full sample to the population to decrease variance. There are potential efficiency advantages from using the two-step approach as well even when the calibration variables employed in each step is a subset of the calibration variables in the single step. Simultaneous mean-squared-error estimation using linearization is possible, but more complicated than when calibrating in a single step.
Release date: 2015-06-29
9. An Update on Depreciation Rates for the Canadian Productivity Accounts Archived
Articles and reports: 15-206-X2015039
Description:
This paper generates updated estimates of depreciation rates to be used in the Canadian Productivity Accounts for the calculation of capital stock and the user cost of capital. Estimates are derived of depreciation profiles for a diverse set of assets, based on patterns of resale prices and retirement ages.
A maximum likelihood technique is used to jointly estimate changes in the valuation of assets over the course of their service life, as well as the nature of the discard process used to dispose of assets to generate depreciation rates. This method is more efficient than others in producing estimates with less bias and higher efficiency.
The earlier estimates that were derived for the period from 1985 to 2001 are compared with those for the latest period, from 2002 to 2010.
Release date: 2015-01-26
10. On Bias Adjustments for Web Surveys Archived
Articles and reports: 11-522-X201300014281
Description:
Web surveys exclude the entire non-internet population and often have low response rates. Therefore, statistical inference based on Web survey samples will require availability of additional information about the non-covered population, careful choice of survey methods to account for potential biases, and caution with interpretation and generalization of the results to a target population. In this paper, we focus on non-coverage bias, and explore the use of weighted estimators and hot-deck imputation estimators for bias adjustment under the ideal scenario where covariate information was obtained for a simple random sample of individuals from the non-covered population. We illustrate empirically the performance of the proposed estimators under this scenario. Possible extensions of these approaches to more realistic scenarios are discussed.
Release date: 2014-10-31

Data (0)

Data (0) (0 results)

No content available at this time.

Analysis (78)

Analysis (78) (0 to 10 of 78 results)

1. A Model-based Disaggregation Method for Estimation of Adult Competency Archived
Articles and reports: 11-522-X202200100003
Description: Estimation at fine levels of aggregation is necessary to better describe society. Small area estimation model-based approaches that combine sparse survey data with rich data from auxiliary sources have been proven useful to improve the reliability of estimates for small domains. Considered here is a scenario where small area model-based estimates, produced at a given aggregation level, needed to be disaggregated to better describe the social structure at finer levels. For this scenario, an allocation method was developed to implement the disaggregation, overcoming challenges associated with data availability and model development at such fine levels. The method is applied to adult literacy and numeracy estimation at the county-by-group-level, using data from the U.S. Program for the International Assessment of Adult Competencies. In this application the groups are defined in terms of age or education, but the method could be applied to estimation of other equity-deserving groups.
Release date: 2024-03-25
2. Measuring the number of food aid recipients Archived
Articles and reports: 11-522-X202200100013
Description: Respondents to typical household surveys tend to significantly underreport their potential use of food aid distributed by associations. This underreporting is most likely related to the social stigma felt by people experiencing great financial difficulty. As a result, survey estimates of the number of recipients of that aid are much lower than the direct counts from the associations. Those counts tend to overestimate due to double counting. Through its adapted protocol, the Enquête Aide alimentaire (EAA) collected in late 2021 in France at a sample of sites of food aid distribution associations, controls the biases that affect the other sources and determines to what extent this aid is used.
Release date: 2024-03-25
3. A method for estimating the effect of classification errors on statistics for two domains
Articles and reports: 12-001-X202300200002
Description: Being able to quantify the accuracy (bias, variance) of published output is crucial in official statistics. Output in official statistics is nearly always divided into subpopulations according to some classification variable, such as mean income by categories of educational level. Such output is also referred to as domain statistics. In the current paper, we limit ourselves to binary classification variables. In practice, misclassifications occur and these contribute to the bias and variance of domain statistics. Existing analytical and numerical methods to estimate this effect have two disadvantages. The first disadvantage is that they require that the misclassification probabilities are known beforehand and the second is that the bias and variance estimates are biased themselves. In the current paper we present a new method, a Gaussian mixture model estimated by an Expectation-Maximisation (EM) algorithm combined with a bootstrap, referred to as the EM bootstrap method. This new method does not require that the misclassification probabilities are known beforehand, although it is more efficient when a small audit sample is used that yields a starting value for the misclassification probabilities in the EM algorithm. We compared the performance of the new method with currently available numerical methods: the bootstrap method and the SIMEX method. Previous research has shown that for non-linear parameters the bootstrap outperforms the analytical expressions. For nearly all conditions tested, the bias and variance estimates that are obtained by the EM bootstrap method are closer to their true values than those obtained by the bootstrap and SIMEX methods. We end this paper by discussing the results and possible future extensions of the method.
Release date: 2024-01-03
4. Relative performance of methods based on model-assisted survey regression estimation: A simulation study
Articles and reports: 12-001-X202200100003
Description:
Use of auxiliary data to improve the efficiency of estimators of totals and means through model-assisted survey regression estimation has received considerable attention in recent years. Generalized regression (GREG) estimators, based on a working linear regression model, are currently used in establishment surveys at Statistics Canada and several other statistical agencies. GREG estimators use common survey weights for all study variables and calibrate to known population totals of auxiliary variables. Increasingly, many auxiliary variables are available, some of which may be extraneous. This leads to unstable GREG weights when all the available auxiliary variables, including interactions among categorical variables, are used in the working linear regression model. On the other hand, new machine learning methods, such as regression trees and lasso, automatically select significant auxiliary variables and lead to stable nonnegative weights and possible efficiency gains over GREG. In this paper, a simulation study, based on a real business survey sample data set treated as the target population, is conducted to study the relative performance of GREG, regression trees and lasso in terms of efficiency of the estimators and properties of associated regression weights. Both probability sampling and non-probability sampling scenarios are studied.

Release date: 2022-06-21
5. Two local diagnostics to evaluate the efficiency of the empirical best predictor under the Fay-Herriot model
Articles and reports: 12-001-X202100200001
Description:
The Fay-Herriot model is often used to produce small area estimates. These estimates are generally more efficient than standard direct estimates. In order to evaluate the efficiency gains obtained by small area estimation methods, model mean square error estimates are usually produced. However, these estimates do not reflect all the peculiarities of a given domain (or area) because model mean square errors integrate out the local effects. An alternative is to estimate the design mean square error of small area estimators, which is often more attractive from a user point of view. However, it is known that design mean square error estimates can be very unstable, especially for domains with few sampled units. In this paper, we propose two local diagnostics that aim to choose between the empirical best predictor and the direct estimator for a particular domain. We first find an interval for the local effect such that the best predictor is more efficient under the design than the direct estimator. Then, we consider two different approaches to assess whether it is plausible that the local effect falls in this interval. We evaluate our diagnostics using a simulation study. Our preliminary results indicate that our diagnostics are effective for choosing between the empirical best predictor and the direct estimator.
Release date: 2022-01-06
6. Reducing the response imbalance: Is the accuracy of the survey estimates improved? Archived
Articles and reports: 12-001-X201600214663
Description:
We present theoretical evidence that efforts during data collection to balance the survey response with respect to selected auxiliary variables will improve the chances for low nonresponse bias in the estimates that are ultimately produced by calibrated weighting. One of our results shows that the variance of the bias – measured here as the deviation of the calibration estimator from the (unrealized) full-sample unbiased estimator – decreases linearly as a function of the response imbalance that we assume measured and controlled continuously over the data collection period. An attractive prospect is thus a lower risk of bias if one can manage the data collection to get low imbalance. The theoretical results are validated in a simulation study with real data from an Estonian household survey.
Release date: 2016-12-20
7. Tests for evaluating nonresponse bias in surveys Archived
Articles and reports: 12-001-X201600214677
Description:
How do we tell whether weighting adjustments reduce nonresponse bias? If a variable is measured for everyone in the selected sample, then the design weights can be used to calculate an approximately unbiased estimate of the population mean or total for that variable. A second estimate of the population mean or total can be calculated using the survey respondents only, with weights that have been adjusted for nonresponse. If the two estimates disagree, then there is evidence that the weight adjustments may not have removed the nonresponse bias for that variable. In this paper we develop the theoretical properties of linearization and jackknife variance estimators for evaluating the bias of an estimated population mean or total by comparing estimates calculated from overlapping subsets of the same data with different sets of weights, when poststratification or inverse propensity weighting is used for the nonresponse adjustments to the weights. We provide sufficient conditions on the population, sample, and response mechanism for the variance estimators to be consistent, and demonstrate their small-sample properties through a simulation study.
Release date: 2016-12-20
8. One step or two? Calibration weighting from a complete list frame with nonresponse Archived
Articles and reports: 12-001-X201500114172
Description:
When a random sample drawn from a complete list frame suffers from unit nonresponse, calibration weighting to population totals can be used to remove nonresponse bias under either an assumed response (selection) or an assumed prediction (outcome) model. Calibration weighting in this way can not only provide double protection against nonresponse bias, it can also decrease variance. By employing a simple trick one can estimate the variance under the assumed prediction model and the mean squared error under the combination of an assumed response model and the probability-sampling mechanism simultaneously. Unfortunately, there is a practical limitation on what response model can be assumed when design weights are calibrated to population totals in a single step. In particular, the choice for the response function cannot always be logistic. That limitation does not hinder calibration weighting when performed in two steps: from the respondent sample to the full sample to remove the response bias and then from the full sample to the population to decrease variance. There are potential efficiency advantages from using the two-step approach as well even when the calibration variables employed in each step is a subset of the calibration variables in the single step. Simultaneous mean-squared-error estimation using linearization is possible, but more complicated than when calibrating in a single step.
Release date: 2015-06-29
9. An Update on Depreciation Rates for the Canadian Productivity Accounts Archived
Articles and reports: 15-206-X2015039
Description:
This paper generates updated estimates of depreciation rates to be used in the Canadian Productivity Accounts for the calculation of capital stock and the user cost of capital. Estimates are derived of depreciation profiles for a diverse set of assets, based on patterns of resale prices and retirement ages.
A maximum likelihood technique is used to jointly estimate changes in the valuation of assets over the course of their service life, as well as the nature of the discard process used to dispose of assets to generate depreciation rates. This method is more efficient than others in producing estimates with less bias and higher efficiency.
The earlier estimates that were derived for the period from 1985 to 2001 are compared with those for the latest period, from 2002 to 2010.
Release date: 2015-01-26
10. On Bias Adjustments for Web Surveys Archived
Articles and reports: 11-522-X201300014281
Description:
Web surveys exclude the entire non-internet population and often have low response rates. Therefore, statistical inference based on Web survey samples will require availability of additional information about the non-covered population, careful choice of survey methods to account for potential biases, and caution with interpretation and generalization of the results to a target population. In this paper, we focus on non-coverage bias, and explore the use of weighted estimators and hot-deck imputation estimators for bias adjustment under the ideal scenario where covariate information was obtained for a simple random sample of individuals from the non-covered population. We illustrate empirically the performance of the proposed estimators under this scenario. Possible extensions of these approaches to more realistic scenarios are discussed.
Release date: 2014-10-31

Reference (2)

Reference (2) ((2 results))

1. Variance estimation with plausible value achievement data: Two STATA programs for use with the YITS/PISA data Archived
Surveys and statistical programs – Documentation: 12-002-X20040016891
Description:
These two programs are designed to estimate variability due to measurement error beyond the sampling variance introduced by the survey design in the Youth in Transition Survey / Programme of International Student Assessment (YITS/PISA). Program code is included in an appendix.
Release date: 2004-04-15
2. Estimation using the generalized weight share method: The case of record linkage Archived
Surveys and statistical programs – Documentation: 11-522-X19990015680
Description:
To augment the amount of available information, data from different sources are increasingly being combined. These databases are often combined using record linkage methods. When there is no unique identifier, a probabilistic linkage is used. In that case, a record on a first file is associated with a probability that is linked to a record on a second file, and then a decision is taken on whether a possible link is a true link or not. This usually requires a non-negligible amount of manual resolution. It might then be legitimate to evaluate if manual resolution can be reduced or even eliminated. This issue is addressed in this paper where one tries to produce an estimate of a total (or a mean) of one population, when using a sample selected from another population linked somehow to the first population. In other words, having two populations linked through probabilistic record linkage, we try to avoid any decision concerning the validity of links and still be able to produce an unbiased estimate for a total of the one of two populations. To achieve this goal, we suggest the use of the Generalised Weight Share Method (GWSM) described by Lavallée (1995).
Release date: 2000-03-02

Report a problem or mistake on this page

Date modified:: 2024-04-25