Show simple item record

dc.contributor.authorCeleux, Gilles
dc.contributor.authorEl Anbari, Mohammed
dc.contributor.authorMarin, Jean-Michel
dc.contributor.authorRobert, Christian P.
dc.date.accessioned2010-10-06T14:10:50Z
dc.date.available2010-10-06T14:10:50Z
dc.date.issued2012
dc.identifier.urihttps://basepub.dauphine.fr/handle/123456789/4911
dc.language.isoenen
dc.subjectBayesian variableen
dc.subjectfrequentist methodsen
dc.subjectregularizationen
dc.subject.ddc519en
dc.subject.classificationjelC11en
dc.titleRegularization in regression: comparing Bayesian and frequentist methods in a poorly informative situationen
dc.typeArticle accepté pour publication ou publié
dc.contributor.editoruniversityotherCNRS : UMR5149 – Université Montpellier II - Sciences et Techniques du Languedoc;France
dc.contributor.editoruniversityotherINRIA – Université Paris Sud - Paris XI – CNRS : UMR;France
dc.contributor.editoruniversityotherINSEE – École Nationale de la Statistique et de l'Administration Économique;France
dc.description.abstractenWe propose a global noninformative approach for Bayesian variable selection that builds on Zellner's g-priors and is similar to Liang et al. (2008). Our proposal does not require any kind of calibration. In the case of a benchmark, we compare Bayesian and frequentist regularization approaches under a low informative constraint when the number of variables is almost equal to the number of observations. The simulated and real dataset experiments we present here highlight the appeal of Bayesian regularization methods, when compared with alternatives. They dominate frequentist methods in the sense they provide smaller prediction errors while selecting the most relevant variables in a parsimonious way.en
dc.relation.isversionofjnlnameBayesian Analysis
dc.relation.isversionofjnlvol7
dc.relation.isversionofjnlissue2
dc.relation.isversionofjnldate2012
dc.relation.isversionofjnlpages477-502
dc.relation.isversionofdoihttp://dx.doi.org/10.1214/12-BA716
dc.identifier.urlsitehttp://fr.arXiv.org/abs/1010.0300en
dc.description.sponsorshipprivateouien
dc.relation.isversionofjnlpublisherInternational Society for Bayesian Analysis
dc.subject.ddclabelProbabilités et mathématiques appliquéesen


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