O empirycznym najlepszym liniowym nieobciążonym predyktorze dla pewnego modelu mieszanego
On empirical best linear unbiased predictor under a Linear Mixed Model with correlated random effects

Summary/Abstract: The problem of small area prediction is considered under a Linear Mixed Model. The article presents a proposal of an empirical best linear unbiased predictor under a model with two correlated random effects. The main aim of the simulation analyses is a study of an influence of the occurrence of a correlation between random effects on properties of the predictor. In the article, an increase of the accuracy due to the correlation between random effects and an influence of model misspecification in cases of the lack of correlation between random effects are analyzed. The problem of the estimation of the Mean Squared Error of the proposed predictor is also considered. The Monte Carlo simulation analyses and the application were prepared in R language.

• Details
• Contents