Deviance information criteria for model selection in approximate Bayesian computation

DOI10.2202/1544-6115.1678MaRDI QIDQ458231zbMATH OpenOpenAlexWikidataFDO

Authors Olivier Francois, Guillaume Laval

Publication date 7 October 2014

Published in Statistical Applications in Genetics and Molecular Biology (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1105.0269

zbMATH Keywords

approximate Bayesian computationmodel choiceinformation criterionexpected deviancepopulation genetic models

Mathematics Subject Classification ID

General biostatistics (92B15)

Abstract: Approximate Bayesian computation (ABC) is a class of algorithmic methods in Bayesian inference using statistical summaries and computer simulations. ABC has become popular in evolutionary genetics and in other branches of biology. However model selection under ABC algorithms has been a subject of intense debate during the recent years. Here we propose novel approaches to model selection based on posterior predictive distributions and approximations of the deviance. We argue that this framework can settle some contradictions between the computation of model probabilities and posterior predictive checks using ABC posterior distributions. A simulation study and an analysis of a resequencing data set of human DNA show that the deviance criteria lead to sensible results in a number of model choice problems of interest to population geneticists.

Recommendations

• Choosing summary statistics by least angle regression for approximate Bayesian computation
• Approximate Bayesian computation with differential evolution
• Semi-automatic selection of summary statistics for ABC model choice
• A new approach to choose acceptance cutoff for approximate Bayesian computation
• Considerate approaches to constructing summary statistics for ABC model selection

Cited in

(14)

• ABC likelihood-free methods for model choice in Gibbs random fields
• Approximate Bayesian model selection with the deviance statistic
• Choosing summary statistics by least angle regression for approximate Bayesian computation
• Considerate approaches to constructing summary statistics for ABC model selection
• A new approach to choose acceptance cutoff for approximate Bayesian computation
• A transdimensional approximate Bayesian computation using the pseudo-marginal approach for model choice
• A rare event approach to high-dimensional approximate Bayesian computation
• Spatial smoothing of low birth weight rate in Bangladesh using Bayesian hierarchical model
• An approximate likelihood perspective on ABC methods
• An approximate Bayesian computation approach for embryonic astrocyte migration model reduction
• Model choice using approximate Bayesian computation and random forests: analyses based on model grouping to make inferences about the genetic history of Pygmy human populations
• A compartmental model for meningitis: separating transmission from climate effects on disease incidence
• A Continuation Method in Bayesian Inference
• Semi-automatic selection of summary statistics for ABC model choice

This page was built for publication: Deviance information criteria for model selection in approximate Bayesian computation

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q458231)