Recursive Pathways to Marginal Likelihood Estimation with Prior-Sensitivity Analysis

被引:28
作者
Cameron, Ewan [1 ]
Pettitt, Anthony [1 ]
机构
[1] Queensland Univ Technol, Fac Sci & Engn, Sch Math Sci Stat Sci, Brisbane, Qld 4001, Australia
关键词
Bayes factor; Bayesian model selection; importance sampling; marginal likelihood; Metropolis-coupled Markov Chain Monte Carlo; nested sampling; normalizing constant; path sampling; reverse logistic regression; thermodynamic integration; MONTE-CARLO METHODS; BAYESIAN DENSITY-ESTIMATION; EMPIRICAL DISTRIBUTIONS; NORMALIZING CONSTANTS; STATISTICAL-MODELS; UNKNOWN NUMBER; SELECTION; MIXTURES; INTEGRATION; SIMULATION;
D O I
10.1214/13-STS465
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 investigate the utility to computational Bayesian analyses of a particular family of recursive marginal likelihood estimators characterized by the (equivalent) algorithms known as "biased sampling" or "reverse logistic regression" in the statistics literature and "the density of states" in physics. Through a pair of numerical examples (including mixture modeling of the well-known galaxy data set) we highlight the remarkable diversity of sampling schemes amenable to such recursive normalization, as well as the notable efficiency of the resulting pseudo-mixture distributions for gauging prior sensitivity in the Bayesian model selection context. Our key theoretical contributions are to introduce a novel heuristic ("thermodynamic integration via importance sampling") for qualifying the role of the bridging sequence in this procedure and to reveal various connections between these recursive estimators and the nested sampling technique.
引用
收藏
页码:397 / 419
页数:23
相关论文
共 89 条
[31]   Choosing among Partition Models in Bayesian Phylogenetics [J].
Fan, Yu ;
Wu, Rui ;
Chen, Ming-Hui ;
Kuo, Lynn ;
Lewis, Paul O. .
MOLECULAR BIOLOGY AND EVOLUTION, 2011, 28 (01) :523-532
[32]   Multimodal nested sampling: an efficient and robust alternative to Markov Chain Monte Carlo methods for astronomical data analyses [J].
Feroz, F. ;
Hobson, M. P. .
MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY, 2008, 384 (02) :449-463
[33]   OPTIMIZED MONTE-CARLO DATA-ANALYSIS [J].
FERRENBERG, AM ;
SWENDSEN, RH .
PHYSICAL REVIEW LETTERS, 1989, 63 (12) :1195-1198
[34]   Marginal likelihood estimation via power posteriors [J].
Friel, N. ;
Pettitt, A. N. .
JOURNAL OF THE ROYAL STATISTICAL SOCIETY SERIES B-STATISTICAL METHODOLOGY, 2008, 70 :589-607
[35]   Estimating the evidence - a review [J].
Friel, Nial ;
Wyse, Jason .
STATISTICA NEERLANDICA, 2012, 66 (03) :288-308
[36]  
GELFAND AE, 1994, J ROY STAT SOC B MET, V56, P501
[37]  
Gelman A, 1998, STAT SCI, V13, P163
[38]  
Gelman A., 1995, Bayesian data analysis, DOI DOI 10.1201/9780429258411
[39]  
GEYER CJ, 1992, J R STAT SOC B, V54, P657
[40]   LARGE SAMPLE THEORY OF EMPIRICAL DISTRIBUTIONS IN BIASED SAMPLING MODELS [J].
GILL, RD ;
VARDI, Y ;
WELLNER, JA .
ANNALS OF STATISTICS, 1988, 16 (03) :1069-1112