An algorithmic construction of all unbiased estimators of variance components in linear mixed effects models
Luyao Peng* and Subir Ghosh University of California, Riverside
The closed form expressions of all unbiased estimators of variance components in linear mixed effects models are presented. The method of moment (MOM) estimators are chosen as benchmarks for finding the unbiased estimators having smaller estimated variances than the corresponding MOM estimators. Examples are presented from small area estimation.
*Presenter
|