A non-iterative sampling Bayesian method for linear mixed models with normal independent distributions

dc.creatorLachos, VH
dc.creatorCabral, CRB
dc.creatorAbanto-Valle, CA
dc.date2012
dc.date2014-08-01T18:16:43Z
dc.date2015-11-26T17:55:59Z
dc.date2014-08-01T18:16:43Z
dc.date2015-11-26T17:55:59Z
dc.date.accessioned2018-03-29T00:39:39Z
dc.date.available2018-03-29T00:39:39Z
dc.identifierJournal Of Applied Statistics. Taylor & Francis Ltd, v. 39, n. 3, n. 531, n. 549, 2012.
dc.identifier0266-4763
dc.identifierWOS:000302020400006
dc.identifier10.1080/02664763.2011.603292
dc.identifierhttp://www.repositorio.unicamp.br/jspui/handle/REPOSIP/76478
dc.identifierhttp://repositorio.unicamp.br/jspui/handle/REPOSIP/76478
dc.identifier.urihttp://repositorioslatinoamericanos.uchile.cl/handle/2250/1291144
dc.descriptionConselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)
dc.descriptionFundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)
dc.descriptionCoordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)
dc.descriptionIn this paper, we utilize normal/independent (NI) distributions as a tool for robust modeling of linear mixed models (LMM) under a Bayesian paradigm. The purpose is to develop a non-iterative sampling method to obtain i.i.d. samples approximately from the observed posterior distribution by combining the inverse Bayes formulae, sampling/importance resampling and posterior mode estimates from the expectation maximization algorithm to LMMs with NI distributions, as suggested by Tan et al. [33]. The proposed algorithm provides a novel alternative to perfect sampling and eliminates the convergence problems of Markov chain Monte Carlo methods. In order to examine the robust aspects of the NI class, against outlying and influential observations, we present a Bayesian case deletion influence diagnostics based on the Kullback-Leibler divergence. Further, some discussions on model selection criteria are given. The new methodologies are exemplified through a real data set, illustrating the usefulness of the proposed methodology.
dc.description39
dc.description3
dc.description531
dc.description549
dc.descriptionConselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)
dc.descriptionFundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)
dc.descriptionCoordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)
dc.descriptionConselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)
dc.descriptionFundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)
dc.descriptionCoordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)
dc.descriptionCNPq [2008/201384-6]
dc.descriptionFAPESP [2008/11455-0]
dc.languageen
dc.publisherTaylor & Francis Ltd
dc.publisherAbingdon
dc.publisherInglaterra
dc.relationJournal Of Applied Statistics
dc.relationJ. Appl. Stat.
dc.rightsfechado
dc.rightshttp://journalauthors.tandf.co.uk/permissions/reusingOwnWork.asp
dc.sourceWeb of Science
dc.subjectGibbs algorithms
dc.subjectinverse Bayes formulae
dc.subjectMCMC
dc.subjectlinear mixed models
dc.subjectnormal/independent distributions
dc.subjectsampling/importance resampling
dc.subjectMultivariate-t-distribution
dc.subjectInfluence Diagnostics
dc.subjectImproper Priors
dc.subjectLocal Influence
dc.subjectRegression
dc.subjectInference
dc.subjectAlgorithms
dc.subjectPosteriors
dc.titleA non-iterative sampling Bayesian method for linear mixed models with normal independent distributions
dc.typeArtículos de revistas


Este ítem pertenece a la siguiente institución