Please use this identifier to cite or link to this item: http://repositorio.unicamp.br/jspui/handle/REPOSIP/348238
Full metadata record
DC FieldValueLanguage
dc.contributor.CRUESPUNIVERSIDADE ESTADUAL DE CAMPINASpt_BR
dc.contributor.authorunicampMedina Garay, Aldo William-
dc.contributor.authorunicampLachos Dávila, Víctor Hugo-
dc.typeArtigopt_BR
dc.titleOn estimation and influence diagnostics for zero-inflated negative binomial regression modelspt_BR
dc.contributor.authorGaray, Aldo M.-
dc.contributor.authorHashimoto, Elizabeth M.-
dc.contributor.authorOrtega, Edwin M. M.-
dc.contributor.authorLachos, Víctor H.-
dc.subjectBootstrap (Estatística)pt_BR
dc.subject.otherlanguageBootstrap (Statistics)pt_BR
dc.description.abstractThe zero-inflated negative binomial model is used to account for overdispersion detected in data that are initially analyzed under the zero-inflated Poisson model. A frequentist analysis, a jackknife estimator and a non-parametric bootstrap for parameter estimation of zero-inflated negative binomial regression models are considered. In addition, an EM-type algorithm is developed for performing maximum likelihood estimation. Then, the appropriate matrices for assessing local influence on the parameter estimates under different perturbation schemes and some ways to perform global influence analysis are derived. In order to study departures from the error assumption as well as the presence of outliers, residual analysis based on the standardized Pearson residuals is discussed. The relevance of the approach is illustrated with a real data set, where it is shown that zero-inflated negative binomial regression models seems to fit the data better than the Poisson counterpartpt_BR
dc.relation.ispartofComputational statistics & data analysispt_BR
dc.relation.ispartofabbreviationComput. stat. data anal.pt_BR
dc.publisher.cityAmsterdam pt_BR
dc.publisher.countryPaíses Baixospt_BR
dc.publisherElsevierpt_BR
dc.date.issued2011-
dc.date.monthofcirculationMar.pt_BR
dc.language.isoengpt_BR
dc.description.volume55pt_BR
dc.description.issuenumber3pt_BR
dc.description.firstpage1304pt_BR
dc.description.lastpage1318pt_BR
dc.rightsFechadopt_BR
dc.sourceWOSpt_BR
dc.identifier.issn0167-9473pt_BR
dc.identifier.eissn1872-7352pt_BR
dc.identifier.doi10.1016/j.csda.2010.09.019pt_BR
dc.identifier.urlhttps://www.sciencedirect.com/science/article/pii/S0167947310003622pt_BR
dc.description.sponsorshipCONSELHO NACIONAL DE DESENVOLVIMENTO CIENTÍFICO E TECNOLÓGICO - CNPQpt_BR
dc.description.sponsorshipFUNDAÇÃO DE AMPARO À PESQUISA DO ESTADO DE SÃO PAULO - FAPESPpt_BR
dc.description.sponsordocumentnumberSem informaçãopt_BR
dc.description.sponsordocumentnumberSem informaçãopt_BR
dc.date.available2020-08-28T15:55:51Z-
dc.date.accessioned2020-08-28T15:55:51Z-
dc.description.provenanceSubmitted by Thais de Brito Barroso (tbrito@unicamp.br) on 2020-08-28T15:55:50Z No. of bitstreams: 0. Added 1 bitstream(s) on 2021-01-04T15:14:33Z : No. of bitstreams: 1 000285663400011.pdf: 675916 bytes, checksum: da1df4ee14aa698cd7593c343387a198 (MD5)en
dc.description.provenanceMade available in DSpace on 2020-08-28T15:55:51Z (GMT). No. of bitstreams: 0 Previous issue date: 2011en
dc.identifier.urihttp://repositorio.unicamp.br/jspui/handle/REPOSIP/348238-
dc.contributor.departmentSem informaçãopt_BR
dc.contributor.departmentDepartamento de Estatísticapt_BR
dc.contributor.unidadeInstituto de Matemática, Estatística e Computação Científicapt_BR
dc.contributor.unidadeInstituto de Matemática, Estatística e Computação Científicapt_BR
dc.subject.keywordEM algorithmpt_BR
dc.subject.keywordGlobal influencept_BR
dc.subject.keywordLocal influencept_BR
dc.subject.keywordNegative binomial distributionpt_BR
dc.subject.keywordZero-inflated modelspt_BR
dc.identifier.source000285663400011pt_BR
dc.creator.orcid0000-0002-4510-639Xpt_BR
dc.creator.orcid0000-0002-7239-2459pt_BR
dc.type.formArtigopt_BR
Appears in Collections:IMECC - Artigos e Outros Documentos

Files in This Item:
File Description SizeFormat 
000285663400011.pdf660.07 kBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.