Drawing on recent 'event history' analytical methods from biostatistics, engineering, and sociology, this clear and comprehensive monograph explains how longitudinal data can be used to study the causes of deaths, crimes, wars, and many other human events. Allison shows why ordinary multiple regression is not suited to analyze event history data, and demonstrates how innovative regression-like methods can overcome this problem. He then discusses the particular new methods that social scientists should find useful.
In virtually every area of the social sciences, there is great interest in events and their causes. Criminologists study crimes, arrests, convictions, and incarcerations. Medical sociologists are concerned with hospitalizations, visits to a physician, and psychotic episodes. In the study of work and careers, ...