The case-control method of determining human cancer causation has developed in the last 20 years as the major epidemiological approach to identify risk factors. Now in paperback, this volume brings together the methods available for analyzing case-control data, and makes them accessible to the practicing epidemiologist and statistician. It expounds both the statistical models and theory behind the methods, and the practical steps of applying them to specific sets of data. All the methods are illustrated with examples from real studies, with an emphasis on the added insight into the data that...

Together with Volume I, this work provides a comprehensive account of the major types of studies in cancer epidemiology. Its scope ranges from an account of elementary and descriptive cohort analyses to the fitting of regression models for incidence rates with general risk functions. Particular attention is given to the use of a case-control approach embedded in a cohort study. As in the first volume, all methods are illustrated by examples from real studies, and the data are appended to the text, enabling readers to rework the computations.