The analysis of registry data in relation to various different types of hypothesis regarding the geographical distribution of disease

Disease registries will often contain the addresses of cases included in the registry. If the registry includes information on all cases, or deaths, occurring in a defined geographical area and time period and if there is a postcode/zip code or map reference for each case it is possible to carry out a variety of different types of geographical analysis that may give clues to the aetiology of the disease. For such analyses it will usually also be necessary to have population data for the region covered by the registry and for separate sub-regions within it. In this paper we review types of analysis that may be applied to such data and give references to examples of applications and the statistical methods used. These include, first, methods of presenting incidence rates, and particularly the use of maps; of particular concern is the development of methods for presenting data that take into account the problems of rates calculated for small populations and which may therefore happen to be high or low simply by chance. Secondly, we consider, the analysis of "clustering" and "clusters" of cases of disease. These problems have been the subject of considerable methodological development in recent years. Analyses of clustering address the question of whether there is a general tendency for there to be aggregations of cases or areas of high incidence the analysis of clusters is concerned with problems of detecting specific locations where there are unusual aggregations of cases. The third type of problem considered here is whether there are, within the registry region, aetiological factors that vary geographically with consequent variations in disease incidence in different sub-regions. Where there is geographical variation it may be possible to use regression analysis to relate such variation to factors such as socio-economic status or levels of some environmental hazard. Finally we consider the problem of determining whether disease rates in certain areas may be related to distance from the source of some potential causative agent.