Attributable Risk Estimation Using Sas/stat Software

In epidemiologic studies devot~d to .the analysis of the relationship between an exposure characteristic and a disease the attributable risk constitutes an interesting epidemiologic risk measure. It can be interpreted as the proportion of cases of disease due to the exposure under study among all cases of disease in the study population. Thus, it indicates the impact of the exposure factor on the disease load of the population and can aid public health administrators in determining promising targets for disease preventive strategies in the population. The estimation of attributable risk from data arranged in contingency tables has received much attention in the statistical literature during recent years. However, none of the leading statistical software packages including SAS has incorporated the attributable risk in the catalogue of measures of association to be automatically calculated in some procedure. In the paper a brief introduction to the theory and application of attributable risk estimation from epidemiologic data is provided. Then, a general method is shown how to calculate attributable risk estimators under the multinomial sampling model usingSAS/STAT* software. Data from the Luebeck Blood Pressure Study, a cross-sectional study in the field of cardiovascular disease epidemiology, are used to illustrate the practical application of the method.