最小二乘估计关于误差分布的稳健性  

On Robustness of LSE in Terms of Error Distributions

作　　者：刘湘蓉[1] 

机构地区：[1]华东师范大学统计系

出　　处：《应用概率统计》2006年第4期429-437,共9页Chinese Journal of Applied Probability and Statistics

摘　　要：对于设计矩阵X是列降秩的线性统计模型,本文讨论了最小二乘估计关于误差分布的稳健性,给出了误差分布的最大类,使得误差项的分布在此范围内变动时,最小二乘估计在均方误差矩阵准则下是最优估计．In this paper, we explore the varing range of the error distributions within which the LSE is the best linear estimator in the sense of minimizing the MSE matrix. We also give the maximal class of distributions of error term for which the LSE possesses a certain kind of robustness.

关 键 词：最小二乘估计 Gauss-Markov定理 均方误差矩阵 广义最小二乘估计 稳健性 

分 类 号：O212.1[理学—概率论与数理统计]