平衡套误差分量回归模型方差分量的估计  

The Estimation of Variance Components in the Banlanced Nested Error Component Regression Model

作　　者：赵静[1] 王磊[1] 

机构地区：[1]滨州学院数学与信息科学系,山东滨州256603

出　　处：《信阳师范学院学报（自然科学版）》2010年第3期343-347,共5页Journal of Xinyang Normal University(Natural Science Edition)

基　　金：滨州学院科学基金项目(BZXYLG200707)

摘　　要：研究了含三个方差分量的平衡套误差分量回归模型,利用Baltagi提出的方差分析型估计—WK估计的方法,得到了套误差分量平衡模型中的对应估计,重点对其改进.对于随机效应和随机误差方差分量的估计,证明了所得到的改进估计在均方误差意义下一致优于按Baltagi方法导出的WK估计,最后还用截尾法给出了随机效应方差分量的正估计.The balanced nested error component regression model with three variance components is studied.With the methods Baltagi used to give the Analysis of Variance（ANOVA）-type estimators—— WK estimators,the corresponding estimators in nested error balanced model is obtained.Furthermore,the improved estimators,aiming at the WK estimators of variance components of random effect and random error are provided respectively,it is proved that the improved estimators are better under mean-squared-error criterion.

关 键 词：套误差分量回归模型 WK估计 改进估计 非负估计 

分 类 号：O212.7[理学—概率论与数理统计]