Likelihood-based Inference with Missing Data Under Missing-at-Random

Cited 3 time in webofscience Cited 0 time in scopus
  • Hit : 385
  • Download : 0
DC FieldValueLanguage
dc.contributor.authorYang, Shuko
dc.contributor.authorKim, Jae Kwangko
dc.date.accessioned2017-01-13T05:07:36Z-
dc.date.available2017-01-13T05:07:36Z-
dc.date.created2016-12-23-
dc.date.created2016-12-23-
dc.date.issued2016-06-
dc.identifier.citationSCANDINAVIAN JOURNAL OF STATISTICS, v.43, no.2, pp.436 - 454-
dc.identifier.issn0303-6898-
dc.identifier.urihttp://hdl.handle.net/10203/218766-
dc.description.abstractLikelihood-based inference with missing data is challenging because the observed log likelihood is often an (intractable) integration over the missing data distribution, which also depends on the unknown parameter. Approximating the integral by Monte Carlo sampling does not necessarily lead to a valid likelihood over the entire parameter space because the Monte Carlo samples are generated from a distribution with a fixed parameter value. We consider approximating the observed log likelihood based on importance sampling. In the proposed method, the dependency of the integral on the parameter is properly reflected through fractional weights. We discuss constructing a confidence interval using the profile likelihood ratio test. A Newton-Raphson algorithm is employed to find the interval end points. Two limited simulation studies show the advantage of the Wilks inference over the Wald inference in terms of power, parameter space conformity and computational efficiency. A real data example on salamander mating shows that our method also works well with high-dimensional missing data.-
dc.languageEnglish-
dc.publisherWILEY-BLACKWELL-
dc.subjectGENERALIZED LINEAR-MODELS-
dc.subjectEM ALGORITHM-
dc.subjectINCOMPLETE DATA-
dc.subjectEMPIRICAL LIKELIHOOD-
dc.subjectMULTIPLE IMPUTATION-
dc.subjectINFORMATION MATRIX-
dc.subjectMAXIMUM-LIKELIHOOD-
dc.subjectDATA AUGMENTATION-
dc.subjectRATIO TESTS-
dc.titleLikelihood-based Inference with Missing Data Under Missing-at-Random-
dc.typeArticle-
dc.identifier.wosid000382553500013-
dc.identifier.scopusid2-s2.0-84949521465-
dc.type.rimsART-
dc.citation.volume43-
dc.citation.issue2-
dc.citation.beginningpage436-
dc.citation.endingpage454-
dc.citation.publicationnameSCANDINAVIAN JOURNAL OF STATISTICS-
dc.identifier.doi10.1111/sjos.12184-
dc.contributor.localauthorKim, Jae Kwang-
dc.contributor.nonIdAuthorYang, Shu-
dc.description.isOpenAccessN-
dc.type.journalArticleArticle-
dc.subject.keywordAuthorconfidence interval-
dc.subject.keywordAuthorfractional imputation-
dc.subject.keywordAuthorlikelihood ratio-
dc.subject.keywordAuthornonresponse-
dc.subject.keywordAuthorprofile likelihood ratio-
dc.subject.keywordPlusGENERALIZED LINEAR-MODELS-
dc.subject.keywordPlusEM ALGORITHM-
dc.subject.keywordPlusINCOMPLETE DATA-
dc.subject.keywordPlusMULTIPLE IMPUTATION-
dc.subject.keywordPlusINFORMATION MATRIX-
dc.subject.keywordPlusMAXIMUM-LIKELIHOOD-
dc.subject.keywordPlusDATA AUGMENTATION-
dc.subject.keywordPlusRATIO TESTS-
Appears in Collection
MA-Journal Papers(저널논문)
Files in This Item
There are no files associated with this item.
This item is cited by other documents in WoS
⊙ Detail Information in WoSⓡ Click to see webofscience_button
⊙ Cited 3 items in WoS Click to see citing articles in records_button

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0