Bayesian latent variable modelling of multivariate spatio-temporal variation in cancer mortality

Abstract

In this article, three alternative Bayesian hierarchical latent factor models are described for spatially and temporally correlated multivariate health data. The fundamentals of factor analysis with ideas of space— time disease mapping to provide a flexible framework for the joint analysis of multiple-related diseases in space and time with a view to estimating common and disease-specific trends in cancer risk are combined. The models are applied to area-level mortality data on six diet-related cancers for Greece over the 20-year period from 1980 to 1999. The aim of this study is to uncover the spatial and temporal patterns of any latent factor(s) underlying the cancer data that could be interpreted as reflecting some aspects of the habitual diet of the Greek population.