UNDERSTANDING THE METROPOLIS-HASTINGS ALGORITHM

被引：2509

作者：

CHIB, S ^{[1
]}

GREENBERG, E ^{[1
]}

机构：

[1] WASHINGTON UNIV,DEPT ECON,ST LOUIS,MO 63130

来源：

AMERICAN STATISTICIAN | 1995年 / 49卷 / 04期

关键词：

GIBBS SAMPLING; MARKOV CHAIN MONTE CARLO; MULTIVARIATE DENSITY SIMULATION; REVERSIBLE MARKOV CHAINS;

D O I：

10.2307/2684568

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：

We provide a detailed, introductory exposition of the Metropolis-Hastings algorithm, a powerful Markov chain method to simulate multivariate distributions. A simple, intuitive derivation of this method is given along with guidance on implementation. Also discussed are two applications of the algorithm, one for implementing acceptance-rejection sampling when a blanketing function is not available and the other for implementing the algorithm with block-at-a-time scans. In the latter situation, many different algorithms, including the Gibbs sampler, are shown to be special cases of the Metropolis-Hastings algorithm. The methods are illustrated with examples.

引用

页码：327 / 335

页数：9

共 24 条

[1]

[Anonymous], 1994, MARKOV CHAINS STOCHA

[2]

BHATTACHARYA RN, 1900, STOCHASTIC PROCESSES

[3]

Billingsley P., 1985, PROBABILITY MEASURE

[4]

Box G.E.P., 1976, TIME SERIES ANAL

[5] EXPLAINING THE GIBBS SAMPLER [J].

CASELLA, G ;

GEORGE, EI .

AMERICAN STATISTICIAN, 1992, 46 (03) :167-174

[6] BAYES INFERENCE IN REGRESSION-MODELS WITH ARMA (P, Q) ERRORS [J].

CHIB, S ;

GREENBERG, E .

JOURNAL OF ECONOMETRICS, 1994, 64 (1-2) :183-206

[7]

CHIB S, 1993, IN PRESS ECONOMETRIC

[8]

Dagpunar J., 1988, PRINCIPLES RANDOM VA

[9] SAMPLING-BASED APPROACHES TO CALCULATING MARGINAL DENSITIES [J].

GELFAND, AE ;

SMITH, AFM .

JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION, 1990, 85 (410) :398-409

[10]

GELMAN A, 1992, COMPUT SCI STAT, V24, P433

← 1 2 3 →