New approaches to compute Bayes factor in finite mixture models

Authors:
M. J. Rufo;J. Martín;C. J. Pérez
Affiliations:
Departamento de Matemáticas, Universidad de Extremadura, Avda. de la Universidad s/n, 10071 Cáceres, Spain;Departamento de Matemáticas, Universidad de Extremadura, Avda. de la Universidad s/n, 10071 Cáceres, Spain;Departamento de Matemáticas, Universidad de Extremadura, Avda. de la Universidad s/n, 10071 Cáceres, Spain
Venue:
Computational Statistics & Data Analysis
Year:
2010

Citing 6
Cited 2

A Bayesian model selection method with applications

Computational Statistics & Data Analysis
Editorial: recent developments in mixture models

Computational Statistics & Data Analysis
Bayesian analysis of finite mixture models of distributions from exponential families

Computational Statistics
Editorial: Advances in Mixture Models

Computational Statistics & Data Analysis
Reversible Jump MCMC in mixtures of normal distributions with the same component means

Computational Statistics & Data Analysis
Bayesian model choice based on Monte Carlo estimates of posterior model probabilities

Computational Statistics & Data Analysis

Editorial: Special issue on variable selection and robust procedures

Computational Statistics & Data Analysis
Editorial: The 2nd special issue on advances in mixture models

Computational Statistics & Data Analysis

Quantified Score

Hi-index	0.03

Visualization

Abstract

Two new approaches to estimate Bayes factors in a finite mixture model context are proposed. Specifically, two algorithms to estimate them and their errors are derived by decomposing the resulting marginal densities. Then, through Bayes factor comparisons, the appropriate number of components for the mixture model is obtained. The approaches are based on simple theory (Monte Carlo methods and cluster sampling), what makes them appealing tools in this context. The performance of both algorithms is studied for different situations and the procedures are illustrated with some previously published data sets.