A default prior distribution for contingency tables with dependent factor levels

A default prior distribution is proposed for the Bayesian analysis of contingency tables. The prior is specified to allow for dependence between levels of the factors. Different dependence structures are considered, including conditional autoregressive and distance correlation structures. To demonst...

Descripción completa

Detalles Bibliográficos
Autores principales: Overstall, Antony M., King, Ruth
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Elsevier 2014
Materias:
Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3990456/
https://www.ncbi.nlm.nih.gov/pubmed/24748854
http://dx.doi.org/10.1016/j.stamet.2013.08.007
_version_ 1782312282912456704
author Overstall, Antony M.
King, Ruth
author_facet Overstall, Antony M.
King, Ruth
author_sort Overstall, Antony M.
collection PubMed
description A default prior distribution is proposed for the Bayesian analysis of contingency tables. The prior is specified to allow for dependence between levels of the factors. Different dependence structures are considered, including conditional autoregressive and distance correlation structures. To demonstrate the prior distribution, a dataset is considered which involves estimating the number of injecting drug users in the eleven National Health Service board regions of Scotland using an incomplete contingency table where the dependence structure relates to geographical regions.
format Online
Article
Text
id pubmed-3990456
institution National Center for Biotechnology Information
language English
publishDate 2014
publisher Elsevier
record_format MEDLINE/PubMed
spelling pubmed-39904562014-04-18 A default prior distribution for contingency tables with dependent factor levels Overstall, Antony M. King, Ruth Stat Methodol Article A default prior distribution is proposed for the Bayesian analysis of contingency tables. The prior is specified to allow for dependence between levels of the factors. Different dependence structures are considered, including conditional autoregressive and distance correlation structures. To demonstrate the prior distribution, a dataset is considered which involves estimating the number of injecting drug users in the eleven National Health Service board regions of Scotland using an incomplete contingency table where the dependence structure relates to geographical regions. Elsevier 2014-01 /pmc/articles/PMC3990456/ /pubmed/24748854 http://dx.doi.org/10.1016/j.stamet.2013.08.007 Text en © 2014 Elsevier B.V. https://creativecommons.org/licenses/by/3.0/This is an open access article under the CC BY license (https://creativecommons.org/licenses/by/3.0/).
spellingShingle Article
Overstall, Antony M.
King, Ruth
A default prior distribution for contingency tables with dependent factor levels
title A default prior distribution for contingency tables with dependent factor levels
title_full A default prior distribution for contingency tables with dependent factor levels
title_fullStr A default prior distribution for contingency tables with dependent factor levels
title_full_unstemmed A default prior distribution for contingency tables with dependent factor levels
title_short A default prior distribution for contingency tables with dependent factor levels
title_sort default prior distribution for contingency tables with dependent factor levels
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3990456/
https://www.ncbi.nlm.nih.gov/pubmed/24748854
http://dx.doi.org/10.1016/j.stamet.2013.08.007
work_keys_str_mv AT overstallantonym adefaultpriordistributionforcontingencytableswithdependentfactorlevels
AT kingruth adefaultpriordistributionforcontingencytableswithdependentfactorlevels
AT overstallantonym defaultpriordistributionforcontingencytableswithdependentfactorlevels
AT kingruth defaultpriordistributionforcontingencytableswithdependentfactorlevels

Ejemplares similares