An alternative to model selection in ordinary regression

被引：9

作者：

Longford, NT ^{[1
]}

机构：

[1] De Montfort Univ, Leicester LE1 9BH, Leics, England

来源：

STATISTICS AND COMPUTING | 2003年 / 13卷 / 01期

关键词：

hypothesis testing; mean squared error; model selection; single-model based estimator; synthetic estimator; two-stage procedure;

D O I：

10.1023/A:1021995912647

中图分类号：

TP301 [理论、方法];

学科分类号：

081202 ;

摘要：

The weaknesses of established model selection procedures based on hypothesis testing and similar criteria are discussed and an alternative based on synthetic (composite) estimation is proposed. It is developed for the problem of prediction in ordinary regression and its properties are explored by simulations for the simple regression. Extensions to a general setting are described and an example with multiple regression is analysed. Arguments are presented against using a selected model for any inferences.

引用

页码：67 / 80

页数：14

共 13 条

[1]

Berger J.O., 1996, Bayesian Stat, V5, P25

[2] MAXIMUM LIKELIHOOD FROM INCOMPLETE DATA VIA EM ALGORITHM [J].