Show simple item record

dc.contributor.authorMokgatlhe, L.
dc.contributor.authorGroenewald, P.C.N.
dc.date.accessioned2013-04-04T06:52:42Z
dc.date.available2013-04-04T06:52:42Z
dc.date.issued2005
dc.identifier.citationMokgatlhe, L. & Groenewald P.C.N. (2005) Bayesian computation for logistic regression, Computational Statistics & Data Analysis, Vol. 48, pp. 857-868en_US
dc.identifier.urihttp://hdl.handle.net/10311/1127
dc.description.abstractA method for the simulation of samples from the exact posterior distributions of the parameters in logistic regression is proposed. It is based on the principle of data augmentation and a latent variable is introduced, similar to the approach of Albert and chib (J. Am. Stat. Assoc. 88 (1993) 669), who applied it to the probit model. In general, the full conditional distributions are intractable, but with the introductions of the latent variable all conditional distributions are uniform, and the Gibbs sampler is easily applicable. Marginal likelihoods for model selection can be obtained at the expense of additional Gibbs cycles. The technique is extended and can be applied with nominal or ordinal polychotomous data.en_US
dc.language.isoenen_US
dc.publisherElsevier, http://www.elsevier.comen_US
dc.subjectData augmentationen_US
dc.subjectBayes factorsen_US
dc.subjectGibbs samplingen_US
dc.subjectLogit modelen_US
dc.subjectOrdinal dataen_US
dc.subjectPolychotomousen_US
dc.subject.lcshLogistic regression analysisen_US
dc.subject.lcshRegression analysisen_US
dc.subject.lcshBayesian statistical decision theoryen_US
dc.subject.lcshSocial sciences--Statistical methodsen_US
dc.titleBayesian computation for logistic regressionen_US
dc.typePublished Articleen_US
dc.linkhttp://www.sciencedirect.com/science/article/pii/S0167947304001148en_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record