On Spectral Decomposition Estimate for a Class of Linear Mixed Models

Abstract:

      The spectral decomposition estimate (SDE) proposed by Wang and Yin$^{[2]}$ is a new method of simultaneously estimating fixed effects and variance components in linear mixed models. In this paper, we furthe study the properties of SDE under linear mixed models with two variance components. We get the necessary and sufficient condition for the equality of the analysis of variance estimate and the SDE of variance components, and show that the SDE of variance components is a uniformly minimum variance unbiased estimte under some conditions.