Bayesian Analysis of Multivariate Count Data

This paper is concerned with the analysis of multivariate count data. A class of models is proposed, based on the work of Aitchison and Ho (1989), in which the correlation amongst the counts is represented by correlated, outcome-specific, latent effects. Several interesting special cases of the model are discussed and a tuned and efficient Markov chain Monte Carlo algorithm is developed to estimate the model. The ideas are illustrated with three real data examples of trivariate to sixteen variate correlated counts.


Issue Date:
Nov 01 1998
Publication Type:
Working or Discussion Paper
Language:
English
Total Pages:
22
Series Statement:
9814




 Record created 2017-09-29, last modified 2017-09-29

Fulltext:
Download fulltext
PDF

Rate this document:

Rate this document:
1
2
3
 
(Not yet reviewed)