Case Studies in Bayesian Statistical Modelling and Analysis

13

Disease Mapping using Bayesian Hierarchical Models

Arul Earnest^1,2 Susanna M. Cramb^3,4 and Nicole M. White^3,5

¹Tan Tock Seng Hospital, Singapore

²Duke-NUS Graduate Medical School, Singapore

³Queensland University of Technology, Brisbane, Australia

⁴Viertel Centre for Research in Cancer Control, Cancer Council Queensland, Australia

⁵CRC for Spatial Information, Australia

13.1 Introduction

Disease mapping falls under the category of spatial epidemiology, which is the description and analysis of geographically indexed health data with respect to demographic, environmental, behavioural, socioeconomic, genetic, and infectious risk factors (Elliott and Wartenberg 2004). Disease maps can be useful for estimating relative risk; ecological analyses, incorporating area and/or individual-level covariates; or cluster analyses (Lawson 2009). As aggregated data are often more readily available, one common method of mapping disease is to aggregate the counts of disease at some geographical areal level, and present them as choropleth maps (Devesa et al. 1999; Population Health Division 2006). Therefore, this chapter will focus exclusively on methods appropriate for areal data.

Some population data are often needed to make meaningful comparisons of disease counts across regions. For instance, an area may have a higher disease count simply because there are more people at risk living in that area. Expected counts of disease are usually calculated, and these expected counts are often standardized ...