File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: An exact non-iterative sampling procedure for discrete missing data problems

TitleAn exact non-iterative sampling procedure for discrete missing data problems
Authors
KeywordsContingency tables
Data augmentation algorithm
EM algorithm
Gibbs sampler
IBF sampler
Markov chain Monte Carlo
Issue Date2007
PublisherBlackwell Publishing Ltd. The Journal's web site is located at http://www.blackwellpublishing.com/journals/STAN
Citation
Statistica Neerlandica, 2007, v. 61 n. 2, p. 232-242 How to Cite?
AbstractMany statistical problems can be formulated as discrete missing data problems (MDPs). Examples include change-point problems, capture and recapture models, sample survey with non-response, zero-inflated Poisson models, medical screening/diagnostic tests and bioassay. This paper proposes an exact non-iterative sampling algorithm to obtain independently and identically distributed (i.i.d.) samples from posterior distribution in discrete MDPs. The new algorithm is essentially a conditional sampling, thus completely avoiding problems of convergence and slow convergence in iterative algorithms such as Markov chain Monte Carlo. Different from the general inverse Bayes formulae (IBF) sampler of Tan, Tian and Ng (Statistica Sinica, 13, 2003, 625), the implementation of the new algorithm requires neither the expectation maximization nor the sampling importance resampling algorithms. The key idea is to first utilize the sampling-wise IBF to derive the conditional distribution of the missing data given the observed data, and then to draw i.i.d. samples from the complete-data posterior distribution. We first illustrate the method with a performing example and then apply the method to contingency tables with one supplemental margin for an human immunodeficiency virus study. © 2007 The Authors. Journal compilation 2007 VVS.
Persistent Identifierhttp://hdl.handle.net/10722/82845
ISSN
2023 Impact Factor: 1.4
2023 SCImago Journal Rankings: 0.575
ISI Accession Number ID
References

 

DC FieldValueLanguage
dc.contributor.authorTian, GLen_HK
dc.contributor.authorTan, Men_HK
dc.contributor.authorNg, KWen_HK
dc.date.accessioned2010-09-06T08:34:05Z-
dc.date.available2010-09-06T08:34:05Z-
dc.date.issued2007en_HK
dc.identifier.citationStatistica Neerlandica, 2007, v. 61 n. 2, p. 232-242en_HK
dc.identifier.issn0039-0402en_HK
dc.identifier.urihttp://hdl.handle.net/10722/82845-
dc.description.abstractMany statistical problems can be formulated as discrete missing data problems (MDPs). Examples include change-point problems, capture and recapture models, sample survey with non-response, zero-inflated Poisson models, medical screening/diagnostic tests and bioassay. This paper proposes an exact non-iterative sampling algorithm to obtain independently and identically distributed (i.i.d.) samples from posterior distribution in discrete MDPs. The new algorithm is essentially a conditional sampling, thus completely avoiding problems of convergence and slow convergence in iterative algorithms such as Markov chain Monte Carlo. Different from the general inverse Bayes formulae (IBF) sampler of Tan, Tian and Ng (Statistica Sinica, 13, 2003, 625), the implementation of the new algorithm requires neither the expectation maximization nor the sampling importance resampling algorithms. The key idea is to first utilize the sampling-wise IBF to derive the conditional distribution of the missing data given the observed data, and then to draw i.i.d. samples from the complete-data posterior distribution. We first illustrate the method with a performing example and then apply the method to contingency tables with one supplemental margin for an human immunodeficiency virus study. © 2007 The Authors. Journal compilation 2007 VVS.en_HK
dc.languageengen_HK
dc.publisherBlackwell Publishing Ltd. The Journal's web site is located at http://www.blackwellpublishing.com/journals/STANen_HK
dc.relation.ispartofStatistica Neerlandicaen_HK
dc.rightsStatistica Neerlandica. Copyright © Blackwell Publishing Ltd.en_HK
dc.subjectContingency tablesen_HK
dc.subjectData augmentation algorithmen_HK
dc.subjectEM algorithmen_HK
dc.subjectGibbs sampleren_HK
dc.subjectIBF sampleren_HK
dc.subjectMarkov chain Monte Carloen_HK
dc.titleAn exact non-iterative sampling procedure for discrete missing data problemsen_HK
dc.typeArticleen_HK
dc.identifier.openurlhttp://library.hku.hk:4550/resserv?sid=HKU:IR&issn=0039-0402&volume=61&issue=2&spage=232&epage=242&date=2007&atitle=An+exact+non-iterative+sampling+procedure+for+discrete+missing+data+problemsen_HK
dc.identifier.emailTian, GL: gltian@hku.hken_HK
dc.identifier.emailNg, KW: kaing@hkucc.hku.hken_HK
dc.identifier.authorityTian, GL=rp00789en_HK
dc.identifier.authorityNg, KW=rp00765en_HK
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1111/j.1467-9574.2007.00345.xen_HK
dc.identifier.scopuseid_2-s2.0-34247615458en_HK
dc.identifier.hkuros138166en_HK
dc.relation.referenceshttp://www.scopus.com/mlt/select.url?eid=2-s2.0-34247615458&selection=ref&src=s&origin=recordpageen_HK
dc.identifier.volume61en_HK
dc.identifier.issue2en_HK
dc.identifier.spage232en_HK
dc.identifier.epage242en_HK
dc.identifier.isiWOS:000245992100004-
dc.publisher.placeUnited Kingdomen_HK
dc.identifier.scopusauthoridTian, GL=25621549400en_HK
dc.identifier.scopusauthoridTan, M=7401464906en_HK
dc.identifier.scopusauthoridNg, KW=7403178774en_HK
dc.identifier.citeulike1271657-
dc.identifier.issnl0039-0402-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats