<abstract xmlns="http://www.w3.org/1999/xhtml"><p>An extensive set of diagnostics for linear regression models has been developed to handle nonsurvey data. The models and the sampling plans used for finite populations often entail stratification, clustering, and survey weights, which renders many of the standard diagnostics inappropriate. In this article we adapt some influence diagnostics that have been formulated for ordinary or weighted least squares for use with stratified, clustered survey data. The statistics considered here include DFBETAS, DFFITS, and Cook's D. The differences in the performance of ordinary least squares and survey-weighted diagnostics are compared using complex survey data where the values of weights, response variables, and covariates vary substantially.</p></abstract>

An extensive set of diagnostics for linear regression models has been developed to handle nonsurvey data. The models and the sampling plans used for finite populations often entail stratification, clustering, and survey weights, which renders many of the standard diagnostics inappropriate. In this article we adapt some influence diagnostics that have been formulated for ordinary or weighted least squares for use with stratified, clustered survey data. The statistics considered here include DFBETAS, DFFITS, and Cook's D. The differences in the performance of ordinary least squares and survey-weighted diagnostics are compared using complex survey data where the values of weights, response variables, and covariates vary substantially.

Linear Regression Diagnostics in Cluster Samples

Westat, 1600 Research Boulevard, Rockville MD 20850, USA

Universities of Michigan and Maryland, 1218 Lefrak Hall, College Park MD 20742, USA

Journal of Official Statistics

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

{"article-title":"Linear Regression Diagnostics in Cluster Samples"}

An extensive set of diagnostics for linear regression models has been developed to handle nonsurvey data. The models and the sampling plans used for finite...

Linear Regression Diagnostics in Cluster Samples

Pubblicato online: 01 mar 2015

Pagine: 61 - 75

Ricevuto: 01 ago 2013

Accettato: 01 set 2014

DOI: https://doi.org/10.1515/jos-2015-0003

Parole chiave
Cook's D, DFBETAS, DFFITS, influence, model fitting, outlier, residuals

© 2015 Jianzhu Li and Richard Valliant

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

Linear Regression Diagnostics in Cluster Samples

Pubblicato online: 01 mar 2015

Pagine: 61 - 75

Ricevuto: 01 ago 2013

Accettato: 01 set 2014

DOI: https://doi.org/10.1515/jos-2015-0003

Parole chiaveCook's D, DFBETAS, DFFITS, influence, model fitting, outlier, residuals

© 2015 Jianzhu Li and Richard Valliant

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

Parole chiave
Cook's D, DFBETAS, DFFITS, influence, model fitting, outlier, residuals