Mean squared error comparisons of the modified ridge regression estimator and the restricted ridge regression estimator

被引：15

作者：

Kaciranlar, S ^{[1
]}

Sakallioglu, S ^{[1
]}

Akdeniz, F ^{[1
]}

机构：

[1] Cukurova Univ, Dept Math, TR-01330 Adana, Turkey

来源：

COMMUNICATIONS IN STATISTICS-THEORY AND METHODS | 1998年 / 27卷 / 01期

关键词：

ridge regression; restricted ridge regression; prior information; mean square error matrix;

D O I：

10.1080/03610929808832655

中图分类号：

O21 [概率论与数理统计]; C8 [统计学];

学科分类号：

020208 ; 070103 ; 0714 ;

摘要：

Swindel (1976) introduced a modified ridge regression estimator based on prior information. Sarkar (1992) suggested a new estimator by combining in a particular way the two approaches followed in obtaining the restricted least squares and ordinary ridge regression estimators. In this paper we compare the mean square error matrices of the modified ridge regression estimator based on prior information and the restricted ridge regression estimator introduced by Sarkar (1992). We stated a sufficient condition for the mean square error matrix of the modified ridge regression estimator to exceed the mean square error matrix of the restricted ridge regression estimator.

引用

页码：131 / 138

页数：8

共 10 条

[1] THE RESTRICTED LEAST-SQUARES ESTIMATOR AND RIDGE-REGRESSION [J].