In this study social indicators and survey measures were used to predict three-year service utilization rates at a community mental health center on a geographic basis. Ten social indicators were selected from available census tract statistics and seven survey measures were taken from an epidemiological survey of the catchment area of the mental health center. These data were analyzed first with univariate analyses of variance and then with step-wise rates. The results showed that mental health utilization rates can be predicted with considerable accuracy by social indicators and survey measures. Combining survey measures and social indicators provided the greatest accuracy; social indicators alone were shown to be more powerful predictors than survey measures alone. Survey measures may be particularly valuable in identifying the special problems of community members, while social indicators provide clues about which geographic areas may have problems. (Author)