Skip to content

Research at St Andrews

A default prior distribution for contingency tables with dependent factor levels

Research output: Contribution to journalArticle


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 involving 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.


Original languageEnglish
Pages (from-to)90-99
Number of pages9
JournalStatistical Methodology
Issue number1
Early online date23 Aug 2013
Publication statusPublished - Jan 2014

    Research areas

  • Contingency table, Dependence strusture, Default prior

Discover related content
Find related publications, people, projects and more using interactive charts.

View graph of relations

Related by journal

  1. A generalised likelihood framework for partially observed capture-recapture-recovery models

    King, R. & McCrea, R. S., 2014, In : Statistical Methodology. 17, p. 30-45

    Research output: Contribution to journalArticle

ID: 28450091