Dropping variables versus use of proxy variables in linear regression

被引：9
|
作者：
Trenkler, G
Stahlecker, P
机构：
[1] UNIV DORTMUND,DEPT STAT,D-44221 DORTMUND,GERMANY
[2] UNIV HAMBURG,DEPT ECON,HAMBURG,GERMANY
来源：
JOURNAL OF STATISTICAL PLANNING AND INFERENCE | 1996年 / 50卷 / 01期
关键词：
dropping variables; proxy variables; linear regression model; mean square error; matrix superiority; admissibility;
D O I：
10.1016/0378-3758(95)00045-3
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：
In this paper we investigate under which conditions it is preferable to use proxies or to omit variables from the linear regression model with respect to the matrix mean square error criterion. Furthermore, some attention is paid to the admissibility of the proxies-based least squares estimator.
引用
收藏
页码：65 / 75
页数：11
相关论文
共 50 条
12345