A new proof of convergence of MCMC via the ergodic theorem

被引：30

作者：

Asmussen, Soren ^{[1
]}

Glynn, Peter W. ^{[2
]}

机构：

[1] Aarhus Univ, Dept Math Sci, DK-8000 Aarhus C, Denmark

[2] Stanford Univ, Dept Management Sci & Engn, Stanford, CA 94305 USA

来源：

STATISTICS & PROBABILITY LETTERS | 2011年 / 81卷 / 10期

关键词：

Markov chain Monte Carlo; Harris recurrence; eta-irreducibility; EXPLORING POSTERIOR DISTRIBUTIONS; MARKOV-CHAINS;

D O I：

10.1016/j.spl.2011.05.004

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：

A key result underlying the theory of MCMC is that any eta-irreducible Markov chain having a transition density with respect to eta and possessing a stationary distribution pi is automatically positive Harris recurrent. This paper provides a short self-contained proof of this fact using the ergodic theorem in its standard form as the most advanced tool. (C) 2011 Elsevier B.V. All rights reserved.

引用

页码：1482 / 1485

页数：4

共 11 条

[1]

[Anonymous], 2004, Springer Texts in Statistics

[2]

[Anonymous], 2007, Stochastic Simulation: Algorithms and Analysis

[3]

[Anonymous], 1995, Markov Chain Monte Carlo in Practice

[4]

Breiman L., 1968, PROBABILITY

[5]

CHAN KS, 1994, ANN STAT, V22, P1747, DOI 10.1214/aos/1176325754

[6]

Durrett R., 2010, PROBABILITY THEORY E

[7]

Kendall W, 2005, LECT NOTES SER INST, V7, P93

[8]

Meyn S.P., 1993, MARKOV CHAINS STOCHA

[9]

NUMMELIN E., 1984, General Irreducible Markov Chains and Non-negative Operators

[10]

Roberts GO, 2004, Probab. Surv., V1, P20, DOI [DOI 10.1214/154957804100000024, 10.1214/154957804100000024]

← 1 2 →