Show simple item record

hal.structure.identifierCommunications, Images et Traitement de l'Information [CITI]
hal.structure.identifierServices répartis, Architectures, MOdélisation, Validation, Administration des Réseaux [SAMOVAR]
dc.contributor.authorDouc, Randal*
hal.structure.identifierCEntre de REcherches en MAthématiques de la DEcision [CEREMADE]
hal.structure.identifierCentre de Recherche en Économie et Statistique [CREST]
dc.contributor.authorRobert, Christian P.*
dc.date.accessioned2010-02-25T09:52:22Z
dc.date.available2010-02-25T09:52:22Z
dc.date.issued2011
dc.identifier.urihttps://basepub.dauphine.fr/handle/123456789/3578
dc.language.isoenen
dc.subjectMetropolis-Hastings algorithmen
dc.subjectcentral limit theoremen
dc.subjectMarkov Chain Monte Carlo (MCMC)en
dc.subjectconditioningen
dc.subjectvariance reductionen
dc.subject.ddc519en
dc.subject.classificationjelC15en
dc.titleA vanilla Rao-Blackwellisation of Metropolis-Hastings algorithmsen
dc.typeArticle accepté pour publication ou publié
dc.description.abstractenCasella and Robert (1996) presented a general Rao--Blackwellisation principle for accept-reject and Metropolis-Hastings schemes that leads to significant decreases in the variance of the resulting estimators, but at a high cost in computing and storage. Adopting a completely different perspective, we introduce instead a universal scheme that guarantees variance reductions in all Metropolis-Hastings~based estimators while keeping the computing cost under control. We establish a central limit theorems for the improved estimators and illustrate their performances on toy examples.en
dc.relation.isversionofjnlnameAnnals of Statistics
dc.relation.isversionofjnlvol39
dc.relation.isversionofjnlissue1
dc.relation.isversionofjnldate2011
dc.relation.isversionofjnlpages261-277
dc.relation.isversionofdoihttp://dx.doi.org/10.1214/10-AOS838
dc.identifier.urlsitehttp://arxiv.org/abs/0904.2144v5en
dc.description.sponsorshipprivateouien
dc.relation.isversionofjnlpublisherInstitute of Mathematical Statistics
dc.subject.ddclabelProbabilités et mathématiques appliquéesen
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