Ordering and improving the performance of Monte Carlo Markov chains

被引：75

作者：

Mira, A ^{[1
]}

机构：

[1] Univ Insubria, Dept Econ, I-21100 Varese, Italy

来源：

STATISTICAL SCIENCE | 2001年 / 16卷 / 04期

关键词：

asymptotic variance; convergence ordering; covariance ordering; efficiency ordering; Metropolis-Hastings algorithm; Peskun ordering; reversible jumps;

D O I：

10.1214/ss/1015346319

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：

An overview of orderings defined on the space of Markov chains having a prespecified unique stationary distribution is given. The intuition gained by studying these orderings is used to improve existing Markov chain Monte Carlo algorithms.

引用

页码：340 / 350

页数：11

共 42 条

[1]

[Anonymous], INTRO MATRIX ANAL

[2]

[Anonymous], 1996, MARKOV CHAIN MONTE C

[3]

[Anonymous], 1955, T AM MATH SOC, DOI [10.1090/S0002-9947-1955-0082655-4, DOI 10.1090/S0002-9947-1955-0082655-4]

[4]

BESAG J, 1993, J ROY STAT SOC B MET, V55, P25

[5]

BESAG J, 2000, 9 CTR STAT SOC SCI

[6] A geometric interpretation of the Metropolis-Hastings algorithm [J].

Billera, LJ ;

Diaconis, P .

STATISTICAL SCIENCE, 2001, 16 (04) :335-339

[7]

BROCKWELL AE, 2001, 757 CARN MELL U

[8] Rao-Blackwellisation of sampling schemes [J].

Casella, G ;

Robert, CP .

BIOMETRIKA, 1996, 83 (01) :81-94

[9]

CHAUVEAU D, 2001, IN PRESS SCAND J STA

[10]

Diaconis P, 2000, ANN APPL PROBAB, V10, P726

← 1 2 3 4 5 →