A note on model uncertainty in linear regression

dc.contributorSwiss Fed Inst Technol
dc.contributorUniversidade Federal de São Carlos (UFSCar)
dc.contributorUniversidade Estadual Paulista (Unesp)
dc.creatorCandolo, C.
dc.creatorDavison, A. C.
dc.creatorDemetrio, CGB
dc.date2015-03-18T15:55:07Z
dc.date2015-03-18T15:55:07Z
dc.date2003-01-01
dc.date.accessioned2023-09-12T03:05:32Z
dc.date.available2023-09-12T03:05:32Z
dc.identifierhttp://dx.doi.org/10.1111/1467-9884.00349
dc.identifierJournal Of The Royal Statistical Society Series D-the Statistician. Oxford: Blackwell Publ Ltd, v. 52, p. 165-177, 2003.
dc.identifier0039-0526
dc.identifierhttp://hdl.handle.net/11449/117077
dc.identifier10.1111/1467-9884.00349
dc.identifierWOS:000183546800003
dc.identifier.urihttps://repositorioslatinoamericanos.uchile.cl/handle/2250/8766562
dc.descriptionWe consider model selection uncertainty in linear regression. We study theoretically and by simulation the approach of Buckland and co-workers, who proposed estimating a parameter common to all models under study by taking a weighted average over the models, using weights obtained from information criteria or the bootstrap. This approach is compared with the usual approach in which the 'best' model is used, and with Bayesian model averaging. The weighted predictor behaves similarly to model averaging, with generally more realistic mean-squared errors than the usual model-selection-based estimator.
dc.descriptionSwiss Fed Inst Technol, Math Inst, CH-1015 Lausanne, Switzerland
dc.descriptionUniv Fed Sao Carlos, BR-13560 Sao Carlos, SP, Brazil
dc.descriptionState Univ Sao Paulo, Piracicaba, Brazil
dc.descriptionState Univ Sao Paulo, Piracicaba, Brazil
dc.format165-177
dc.languageeng
dc.publisherBlackwell Publ Ltd
dc.relationJournal Of The Royal Statistical Society Series D-the Statistician
dc.rightsAcesso restrito
dc.sourceWeb of Science
dc.subjectakaike information criterion
dc.subjectBayes information criterion
dc.subjectbootstrap
dc.subjectmodel averaging
dc.subjectmodel uncertainty
dc.subjectprediction
dc.titleA note on model uncertainty in linear regression
dc.typeArtigo


Este ítem pertenece a la siguiente institución