Weighting in Regression for Use in Survey Methodology

by James R. Knaub, Jr .

Abstract: Weighted linear regression models have been developed for use in the estimation of totals and variances for survey data. (Consider works by Brewer, and by Royall and Cumberland, etc.) Weighted linear regression models have also been developed for prediction and variance studies in analyses of physical and biological data. (Consider works by Carroll and Ruppert, etc.) There are similarities and differences between these approaches. This paper considers this and deduces further implications for survey methodology. Application guidelines are discussed.

Key Words: estimation, prediction, heteroscedasticity, variance of a variance function parameter, establishment surveys, model-based inference, stratification, sampling, imputation

James R. Knaub, Jr., jknaub@eia.doe.gov

Editor: Jeffrey S. Simonoff , jsimonoff@stern.nyu.edu

READING THE ARTICLE: You can read the article in portable document (.pdf) format (377580 bytes.)
Errata (in .pdf format).

NOTE: The content of this article is the intellectual property of the authors, who retains all rights to future publication.

This page has been accessed 2846 times since July 24, 2006.

Return to the InterStat Home Page.