Bayesian auxiliary variable models for binary and multinomial regression

In this paper we discuss auxiliary variable approaches to Bayesian binary and multinomial regression. These approaches are ideally suited to automated Markov chain Monte Carlo simulation. In the first part we describe a simple technique using joint updating that improves the performance of the conve...

Ausführliche Beschreibung

Bibliographische Detailangaben
Hauptverfasser: Holmes, C, Held, L
Format: Journal article
Sprache:English
Veröffentlicht: 2006
_version_ 1826282327489118208
author Holmes, C
Held, L
author_facet Holmes, C
Held, L
author_sort Holmes, C
collection OXFORD
description In this paper we discuss auxiliary variable approaches to Bayesian binary and multinomial regression. These approaches are ideally suited to automated Markov chain Monte Carlo simulation. In the first part we describe a simple technique using joint updating that improves the performance of the conventional probit regression algorithm. In the second part we discuss auxiliary variable methods for inference in Bayesian logistic regression, including covariate set uncertainty. Finally, we show how the logistic method is easily extended to multinomial regression models. All of the algorithms are fully automatic with no user set parameters and no necessary Metropolis-Hastings accept/reject steps. © 2006 International Society for Bayesian Analysis.
first_indexed 2024-03-07T00:42:10Z
format Journal article
id oxford-uuid:836d1da8-0202-4c8c-a229-32b80d6fe742
institution University of Oxford
language English
last_indexed 2024-03-07T00:42:10Z
publishDate 2006
record_format dspace
spelling oxford-uuid:836d1da8-0202-4c8c-a229-32b80d6fe7422022-03-26T21:44:01ZBayesian auxiliary variable models for binary and multinomial regressionJournal articlehttp://purl.org/coar/resource_type/c_dcae04bcuuid:836d1da8-0202-4c8c-a229-32b80d6fe742EnglishSymplectic Elements at Oxford2006Holmes, CHeld, LIn this paper we discuss auxiliary variable approaches to Bayesian binary and multinomial regression. These approaches are ideally suited to automated Markov chain Monte Carlo simulation. In the first part we describe a simple technique using joint updating that improves the performance of the conventional probit regression algorithm. In the second part we discuss auxiliary variable methods for inference in Bayesian logistic regression, including covariate set uncertainty. Finally, we show how the logistic method is easily extended to multinomial regression models. All of the algorithms are fully automatic with no user set parameters and no necessary Metropolis-Hastings accept/reject steps. © 2006 International Society for Bayesian Analysis.
spellingShingle Holmes, C
Held, L
Bayesian auxiliary variable models for binary and multinomial regression
title Bayesian auxiliary variable models for binary and multinomial regression
title_full Bayesian auxiliary variable models for binary and multinomial regression
title_fullStr Bayesian auxiliary variable models for binary and multinomial regression
title_full_unstemmed Bayesian auxiliary variable models for binary and multinomial regression
title_short Bayesian auxiliary variable models for binary and multinomial regression
title_sort bayesian auxiliary variable models for binary and multinomial regression
work_keys_str_mv AT holmesc bayesianauxiliaryvariablemodelsforbinaryandmultinomialregression
AT heldl bayesianauxiliaryvariablemodelsforbinaryandmultinomialregression