Show simple item record

Recentered importance sampling with applications to Bayesian model validation

hal.structure.identifier
dc.contributor.authorNur, Darfiana*
hal.structure.identifier
dc.contributor.authorMengersen, Kerrie*
hal.structure.identifier
dc.contributor.authorMcVinish, Ross*
dc.date.accessioned2012-02-28T13:51:58Z
dc.date.available2012-02-28T13:51:58Z
dc.date.issued2013
dc.identifier.urihttps://basepub.dauphine.fr/handle/123456789/8311
dc.language.isoenen
dc.subjectBayesian modelingen
dc.subjectMCMCen
dc.subjectp-valuesen
dc.subjectimportance samplingen
dc.subjectgoodness of fiten
dc.subjectcurse of dimensionalityen
dc.subject.ddc519en
dc.subject.classificationjelC15en
dc.subject.classificationjelC11en
dc.titleRecentered importance sampling with applications to Bayesian model validationen
dc.typeArticle accepté pour publication ou publié
dc.contributor.editoruniversityotherFaculte des sciences Pharmaceutiques et biologiques Université Paris V - Paris Descartes;France
dc.contributor.editoruniversityotherCentre de Recherche en Économie et Statistique (CREST) http://www.crest.fr/ INSEE – École Nationale de la Statistique et de l'Administration Économique;France
dc.contributor.editoruniversityotherSchool of Mathematical and physical Sciences http://www.newcastle.edu.au/school/mathematical-physical-sciences/ University of Newcastle;Australie
dc.contributor.editoruniversityotherQueensland University ot Technolgy (QUT) Queensland University ot Technolgy;Australie
dc.contributor.editoruniversityotherschool of mathematical sciences Queensland University of Technology school of Mathematical Sciences, Queensland University of Technology, Brisbane;Australie
dc.description.abstractenSince its introduction in the early 90's, the idea of using importance sampling (IS) with Markov chain Monte Carlo (MCMC) has found many applications. This paper examines problems associated with its application to repeated evaluation of related posterior distributions with a particular focus on Bayesian model validation. We demonstrate that, in certain applications, the curse of dimensionality can be reduced by a simple modi - cation of IS. In addition to providing new theoretical insight into the behaviour of the IS approximation in a wide class of models, our result facilitates the implementation of computationally intensive Bayesian model checks. We illustrate the simplicity, computational savings and potential inferential advantages of the proposed approach through two substantive case studies, notably computation of Bayesian p-values for linear regression models and simulation-based model checking. Supplementary materials including appendices and the R code for Section 3.1.2 are available online.en
dc.relation.isversionofjnlnameJournal of Computational and Graphical Statistics
dc.relation.isversionofjnlvol22
dc.relation.isversionofjnlissue1
dc.relation.isversionofjnldate2013
dc.relation.isversionofjnlpages215-228
dc.relation.isversionofdoihttp://dx.doi.org/10.1080/10618600.2012.681239
dc.identifier.urlsitehttp://hal.archives-ouvertes.fr/hal-00641483en
dc.description.sponsorshipprivateouien
dc.relation.isversionofjnlpublisherTaylor and Francis
dc.subject.ddclabelProbabilités et mathématiques appliquéesen
hal.author.functionaut
hal.author.functionaut
hal.author.functionaut


Files in this item

FilesSizeFormatView

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record