ASYMPTOTIC PROPERTIES OF THE EMPIRICAL BLUP AND BLUE IN MIXED LINEAR-MODELS

We show in a general mixed model the best linear unbiased estimators ( BLUE) of fixed effects, with unknown variance components substituted b y the REML estimates, are jointly asymptotically normal with the REML estimates. We also prove that given sufficient information the empiric al distributions of the best linear unbiased predictors (BLUP) of rand om effects, again with REML-estimated variance components, converge to the true distributions of the corresponding random effects. As a cons equence, we obtain a consistent estimate of the asymptotic variance-co variance matrix of the REML estimates. The results require neither tha t the data is normally distributed nor that the model is hierarchical (nested).