方差分量谱分解估计的几个性质(英文)  

Some Properties of Spectral Decomposition Estimate of Variance Components

作　　者：史建红[1] 王松桂[1] 

机构地区：[1]北京工业大学应用数理学院,北京100022

出　　处：《应用概率统计》2004年第3期287-294,共8页Chinese Journal of Applied Probability and Statistics

基　　金：The work was supported by the National Natural Science Foundation of China(10271010);the Natural Science Foundation of Beijing(1032001).

摘　　要：对于线性混合模型中方差分量的估计,虽有多种方法,但一般情况下只有方差分析估计和谱分解估计有显式解.本文就线性混合模型中含两个方差分量的情形,对方差分析估计和谱分解估计进行了比较,证明了在一些条件下两个估计的方差相等,由此推出谱分解估计也具有方差分析估计的某些优良性.文末用实例进一步说明了文中的结果.Although there exist many estimates of variance components in linear mixed effects models, only the spectral decomposition estimate (SDE) and analysis of variance estimate (ANOVAE) have closed form in the general case. In this paper we compare the SDE with the ANOVAE in the linear mixed model with two variance components. Our results show that these two estimates of the variance components have the equal variance under some conditions. Thus the SDE shares some optimalities of the ANOVAE. Two examples are given to illustrate our theoretical results.

关 键 词：谱分解估计 方差分析估计 方差分量 线性混合模型 

分 类 号：O212.1[理学—概率论与数理统计]