Covariate adjusted mixture models and disease mapping with the program DismapWin.

The analysis and recognition of disease clustering in space and its representation on a map is an important problem in epidemiology. An approach using mixture models to identify spatial heterogeneity in disease risk and map construction within an empirical Bayes framework is described. Once heterogeneity is detected, the question arises as how explanatory variables could be included in the model. A mixed Poisson regression approach to include covariates is presented. The methods are illustrated using data for tuberculosis from Berlin in 1991.