A Hellinger distance approach to MCMC diagnostics

被引：24

作者：

Boone, Edward L. ^{[1
]}

Merrick, Jason R. W. ^{[1
]}

Krachey, Matthew J. ^{[2
]}

机构：

[1] Virginia Commonwealth Univ, Dept Stat Sci & Operat Res, Richmond, VA 23284 USA

[2] N Carolina State Univ, Dept Biol, Raleigh, NC 27695 USA

来源：

JOURNAL OF STATISTICAL COMPUTATION AND SIMULATION | 2014年 / 84卷 / 04期

关键词：

Hellinger distance; kernel density estimation; Markov chain Monte Carlo; Bayesian robustness; CHAIN MONTE-CARLO; GIBBS SAMPLER; CONVERGENCE ASSESSMENT; INITIALIZATION BIAS; MARKOV; ESTIMATORS;

D O I：

10.1080/00949655.2012.729588

中图分类号：

TP39 [计算机的应用];

学科分类号：

081203 ; 0835 ;

摘要：

Bayesian analysis often requires the researcher to employ Markov Chain Monte Carlo (MCMC) techniques to draw samples from a posterior distribution which in turn is used to make inferences. Currently, several approaches to determine convergence of the chain as well as sensitivities of the resulting inferences have been developed. This work develops a Hellinger distance approach to MCMC diagnostics. An approximation to the Hellinger distance between two distributions f and g based on sampling is introduced. This approximation is studied via simulation to determine the accuracy. A criterion for using this Hellinger distance for determining chain convergence is proposed as well as a criterion for sensitivity studies. These criteria are illustrated using a dataset concerning the Anguilla australis, an eel native to New Zealand.

引用

页码：833 / 849

页数：17

共 36 条

[1] Convergence assessment techniques for Markov chain Monte Carlo [J].

Brooks, SP ;

Roberts, GO .

STATISTICS AND COMPUTING, 1998, 8 (04) :319-335

[2] Efficient construction of reversible jump Markov chain Monte Carlo proposal distributions [J].

Brooks, SP ;

Giudici, P ;

Roberts, GO .

JOURNAL OF THE ROYAL STATISTICAL SOCIETY SERIES B-STATISTICAL METHODOLOGY, 2003, 65 :3-39

[3] Nonparametric convergence assessment for MCMC model selection [J].

Brooks, SP ;

Giudici, P ;

Philippe, A .

JOURNAL OF COMPUTATIONAL AND GRAPHICAL STATISTICS, 2003, 12 (01) :1-22

[4] General methods for monitoring convergence of iterative simulations [J].

Brooks, SP ;

Gelman, A .

JOURNAL OF COMPUTATIONAL AND GRAPHICAL STATISTICS, 1998, 7 (04) :434-455

[5] Kernel estimation for stationary density of Markov chains with general state space [J].

Campos, VSM ;

Dorea, CCY .

ANNALS OF THE INSTITUTE OF STATISTICAL MATHEMATICS, 2005, 57 (03) :443-453

[6]

Conover W.J, 1971, Practical nonparametric statistics

[7] Markov chain Monte Carlo convergence diagnostics: A comparative review [J].

Cowles, MK ;

Carlin, BP .

JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION, 1996, 91 (434) :883-904

[8] A working guide to boosted regression trees [J].

Elith, J. ;

Leathwick, J. R. ;

Hastie, T. .

JOURNAL OF ANIMAL ECOLOGY, 2008, 77 (04) :802-813

[9] Markov chain Monte Carlo: Can we trust the third significant figure? [J].

Flegal, James M. ;

Haran, Murali ;

Jones, Galin L. .

STATISTICAL SCIENCE, 2008, 23 (02) :250-260

[10] BATCH MEANS AND SPECTRAL VARIANCE ESTIMATORS IN MARKOV CHAIN MONTE CARLO [J].

Flegal, James M. ;

Jones, Galin L. .

ANNALS OF STATISTICS, 2010, 38 (02) :1034-1070

← 1 2 3 4 →