摘要
两向分类随机效应模型是一种有着广泛应用的统计模型,对其中的方差分量,经常使用方差分析法来估计。本文中,在均方损失意义下,给出了一种简单易行地改进ANOVA估计的方法,并给出了方差分量的正估计,这个估计在均方损失下一致优于ANOVA估计。
Two way classification models with random effects are used widely. The variance com- ponents in these models are often estimated by ANOVA estimates. In this article, we improve the ANOVA estimates in the sense of mean square errors by an easy way. Also we construct nonnegative estimates of variance components which have smaller mean square errors than ANOVA estimates.
出处
《工程数学学报》
CSCD
北大核心
2007年第2期303-310,共8页
Chinese Journal of Engineering Mathematics
基金
北京市属市管高等学校人才强教计划资助项目.
关键词
两向分量随机效应模型
线性混合模型
非负估计
方差分析估计
two wav classification model
analysis of variance estimate
nonnegative estimate
linear mixed models
