BAYESIAN MODEL CHOICE VIA MARKOV-CHAIN MONTE-CARLO METHODS

被引：13

作者：

CARLIN, BP ^{[1
]}

CHIB, S ^{[1
]}

机构：

[1] WASHINGTON UNIV,ST LOUIS,MO

来源：

JOURNAL OF THE ROYAL STATISTICAL SOCIETY SERIES B-METHODOLOGICAL | 1995年 / 57卷 / 03期

关键词：

BAYES FACTOR; FINITE MIXTURE MODEL; GIBES SAMPLER; INTEGER-VALUED PARAMETERS; MODELS OF VARYING SIZE; MULTIPLE CHANGEPOINT MODEL; NONNESTED MODELS;

D O I：

暂无

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：

Markov chain Monte Carlo (MCMC) integration methods enable the fitting of models of virtually unlimited complexity, and as such have revolutionized the practice of Bayesian data analysis. However, comparison across models may not proceed in a completely analogous fashion, owing to violations of the conditions sufficient to ensure convergence of the Markov chain. In this paper we present a framework for Bayesian model choice, along with an MCMC algorithm that does not suffer from convergence difficulties. Our algorithm applies equally well to problems where only one model is contemplated but its proper size is not known at the outset, such as problems involving integer-valued parameters, multiple changepoints or finite mixture distributions. We illustrate our approach with two published examples.

引用

页码：473 / 484

页数：12

共 26 条

[11] VARIABLE SELECTION VIA GIBBS SAMPLING
GEORGE, EI
MCCULLOCH, RE
[J]. JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION, 1993, 88 (423) : 881 - 889
[12] GREEN PJ, 1994, BAYESIAN ANAL MULTIP
[13] GRENANDER U, 1994, J R STAT SOC B, V56, P549
[14] KASS RE, 1995, IN PRESS J AM STATIS
[15] MCCULLOCH RE, 1994, COMPUTING SCI STATIS, P253
[16] NEWTON MA, 1994, J R STAT SOC B, V56, P3
[17] Olkin I., 1992, J COMPUTATIONAL GRAP, V1, P351
[18] PROBES OF LARGE-SCALE STRUCTURE IN THE CORONA BOREALIS REGION
POSTMAN, M
HUCHRA, JP
GELLER, MJ
[J]. ASTRONOMICAL JOURNAL, 1986, 92 (06) : 1238 - 1247
[19] Ripley B., 1987, STOCHASTIC SIMULATIO
[20] ROBERTS GO, 1993, STOCHASTIC PROCESSES, V49, P207

← 1 2 3 →