Comparison of Estimators of Heteroscedastic Variances in Linear Models.
Abstract
Three methods for estimating heteroscedastic variances are discussed in the paper: the MINQUE introduced by C. R. Rao, the AUE introduced by Duncan, Horn, and Horn, and the sample variance. Properties of these estimators, including translation invariance, existence, bias, consistency, existence of negative estimates, and mean square error are compared. In particular, it is shown that the AUE has smaller mean square error than either the MINQUE or the sample variance in a wide range of situations. (Author)
Document Details
- Document Type
- Technical Report
- Publication Date
- Aug 01, 1973
- Accession Number
- AD0769398
Entities
People
- Roger A. Horn
- Susan D. Horn
Organizations
- Johns Hopkins University