矩阵损失下带约束的回归系数Minimax可容许性的特征  

THE MINIMAX ADMISSIBILITY CHARACTERIZATION OF HOMOGENEOUS LINEAR ESTIMATES WITH RESPECT TO RESTRICTED REGRESSION COEFFICIENT UNDER MATRIX LOSS FUNCTION

作　　者：谭萄[1] 王成名[1] 

机构地区：[1]广西师范大学数学与计算机科学系

出　　处：《广西师范大学学报（自然科学版）》1999年第1期40-46,共7页Journal of Guangxi Normal University:Natural Science Edition

摘　　要：在矩阵损失下给出了带约束回归系数线性估计在齐次线性估计类中是Ｍｉｎｉｍａｘ可容许估计的充要条件This paper discusses the Minimax admissibility characterization of linear estimates with respect to restricted regression coefficient under a matrix loss function. The necessary and sufficient conditions are given for a linear estimate LY to be Minimax admissibe in the class of homogeneous linear estimates.

关 键 词：矩阵损失 线性估计 回归系数 可容许性 损失函数 

分 类 号：O211.67[理学—概率论与数理统计] O212.1[理学—数学]