Spatial and temporal analysis of disease occurrence for detection of clustering

Abstract

Data on disease occurrence often consist of the number of cases recorded in a set of regions during each of several time periods. In this paper a method of analysis of such data is proposed which allows one to distinguish and test for spatial clustering, temporal clustering, and space-time clustering of cases. Departures of case numbers from expectation are partitioned into region and time period main effects and region-by-time interactions. Spatial and temporal relationships among regions and time periods are incorporated by pooling estimates over neighborhoods. In addition to providing tests for clustering, the analysis identifies the contributions to clustering made by individual neighborhoods. Data on Creutzfeldt-Jakob disease in France are used to illustrate the approach.