线性模型中回归系数的c-K型估计及其优良性  

The c-K Class Estimator of Coefficients in Linear Regression Models and its Optimality

作　　者：万雄波[1] 叶鹰[1] 

机构地区：[1]华中科技大学数学系,湖北武汉430074

出　　处：《湖北工业大学学报》2008年第1期89-91,共3页Journal of Hubei University of Technology

摘　　要：将张建军等人提出的c-k估计推广至c-K估计的情形,证明了在均方误差意义下利用Stein压缩技术可以改进广义岭估计,并给出了下c-K估计优于最小二乘估计的一个充分条件,为病态线性回归模型系数的有偏估计提供了改进的技术途径.The c-K class estimator proposed by Zhang Jian-jun is extended to the c-k class estimator in this paper and it is proved that the generalized ridge regression estimators can be improved by applying the idea of James-Stein regression technique. Under the mean square error matrix criterion, a sufficient condition on which the c-K class estimator has an advantage over the least square estimator is presented. The method proposed in this paper provides a technical way to the improvement of the biased estimation.

关 键 词：c-K型估计 STEIN估计 最小二乘估计 均方误差矩阵准则 

分 类 号：O212.1[理学—概率论与数理统计]