线性混合模型中方差分量的非负估计  

Nonnegative Estimation of Variance Components in Linear Mixed Effects Models

作　　者：杨戍[1] 高惠[2] 

机构地区：[1]华北科技学院基础部,北京101601 [2]石家庄职业技术学院基础部,河北石家庄050081

出　　处：《河北师范大学学报（自然科学版）》2010年第3期275-279,共5页Journal of Hebei Normal University：Natural Science

基　　金：国家自然科学基金(10261003)

摘　　要：在线性混合效应模型中,方差分量的非负估计问题备受关注.基于方差分量的ANOVA估计,给出了方差分量的不依赖于随机效应分布的非负改进,且改进后的估计在均方误差意义下优于ANOVA估计,有比ANO-VA估计更好的极限性质.当随机效应和随机误差都服从正态分布时,模拟显示,新估计优于ANOVA估计以及Tatsuya估计.Nonnegative estimator of variance components in linear mixed effects model are proposed based on their ANOVA estimator.These estimators have less mean squared errors than ANOVA estimator,and do not depend on the distributions of random effects.When random effects and errors are normal distribution,simulation shows that the new estimators are better than ANOVEA estimator and Tatsuya estimator in the sense of mean squared error.

关 键 词：线性混合效应模型 方差分量 非负估计 方差分析估计 随机效应 

分 类 号：O212.4[理学—概率论与数理统计]