Approximations and consistency of Bayes factors as model dimension grows

被引：55

作者：

Berger, JO

Ghosh, JK

Mukhopadhyay, N

机构：

[1] Purdue Univ, Eli Lilly & Co, LCC, Indianapolis, IN 46285 USA

[2] Duke Univ, Durham, NC 27706 USA

来源：

JOURNAL OF STATISTICAL PLANNING AND INFERENCE | 2003年 / 112卷 / 1-2期

基金：

美国国家科学基金会;

关键词：

model selection; Bayes factor; BIC; asymptotic consistency;

D O I：

10.1016/S0378-3758(02)00336-1

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：

Stone (J. Roy. Statist. Soc. Ser. B 41 (1979) 276) showed that BIC can fail to be asymptotically consistent. Note, however, that BIC was developed as an asymptotic approximation to Bayes factors between models, and that the approximation is valid only under certain conditions.. The counterexample of Stone arises in situations in which BIC is not an adequate approximation. We develop some new approximations to Bayes factors, that are valid for the situation considered in Stone (1979) and discuss related issues of consistency. (C) 2002 Elsevier Science B.V. All rights reserved.

引用

页码：241 / 258

页数：18

共 11 条

[1]

Abramowitz M., 1970, HDB MATH FUNCTIONS, V55

[2] The intrinsic Bayes factor for model selection and prediction [J].