A test of significance for geographic clusters of disease

Abstract

The geographic pattern of disease has been visually studied by depicting the categorized mortality or morbidity rates on a map. Visual study, however, by no means indicates the statistical significance of observed clusters, i.e., whether or not the geographic aggregations could occur by chance alone. In this paper, an approach for assessing the deviation from chance expectation of the geographic pattern actually observed on the map is described. A simple chi-square test is proposed, and its validity is substantiated by a Monte Carlo approach, which is derived analytically as a special case of Knox's test for space--time clustering. The parameters required for the test are (1) total number of areas, (2) numbers of subareas for each mortality of morbidity category, (3) total number of geographically adjacent areas, and (4) observed numbers of adjacent areas having concordant category pairs.