On perfect simulation for some mixtures of distributions

被引：15

作者：

Hobert, JP

Robert, CP

Titterington, DM

机构：

[1] Univ Florida, Dept Stat, Gainesville, FL 32611 USA

[2] Univ Rouen, CNRS, UPRES A 6085, F-75675 Paris 14, France

[3] CREST, INSEE, F-75675 Paris 14, France

[4] Univ Glasgow, Dept Stat, Glasgow G12 8QQ, Lanark, Scotland

来源：

STATISTICS AND COMPUTING | 1999年 / 9卷 / 04期

关键词：

coupling; gamma decomposition; Gibbs sampling; monotonicity;

D O I：

10.1023/A:1008912006771

中图分类号：

TP301 [理论、方法];

学科分类号：

081202 ;

摘要：

This paper studies the implementation of the coupling from the past (CFTP) method of Propp and Wilson (1996) in the set-up of two and three component mixtures with known components and unknown weights. We show that monotonicity structures can be exhibited in both cases, but that CFTP can still be costly for three component mixtures. We conclude with a simulation experiment exhibiting an almost perfect sampling scheme where we only consider a subset of the exhaustive set of starting values.

引用

页码：287 / 298

页数：12

共 13 条

[1]

DIEBOLT J, 1994, J ROY STAT SOC B MET, V56, P363

[2]

Fill JA, 1998, ANN APPL PROBAB, V8, P131

[3]

Green PJ, 1999, BAYESIAN STATISTICS 6, P301

[4] Characterization results and Markov chain Monte Carlo algorithms including exact simulation for some spatial point processes [J].