线性回归模型的一个新的随机约束岭估计  

A New Random Restricted Ridge Estimator in Linear Regression Model

作　　者：司童文[1] 

机构地区：[1]华盛顿大学艺术与科学学院,美国西雅图981953765

出　　处：《石家庄铁道大学学报（自然科学版）》2012年第3期107-110,共4页Journal of Shijiazhuang Tiedao University(Natural Science Edition)

摘　　要：研究带随机先验信息的线性回归模型,提出一种新的随机约束岭估计,得到新的估计在均方误差矩阵意义下优于混合估计、普通岭估计、随机混合估计(Yalian,2008)和另一随机混合估计(富月,2003)的充要条件。理论结果与数值实验都表明:新的估计在均方误差矩阵意义下的性能是优良的。We are concerned with the parameter estimation in linear regression model with random prior in- formation. A new random restricted ridge estimator is introduced and their properties are discussed. The necessa- ry and sufficient conditions that the new estimator is better than the mixed estimator, the ordinary ridge estima- tor, the stochastic mixed estimator （Yalian Li,2008） and the another random mixed estimator （Yue Fu, 2003） in terms of the mean squared error matrix are obtained. The results of theorems and numerical examples show that the performance of the new estimator is perfect in the terms of the mean squared error matrix.

关 键 词：岭估计 混合估计 随机约束岭估计 随机混合估计 均方误差矩阵 

分 类 号：O211.5[理学—概率论与数理统计]