Event history analysis has been a useful method in the social sciences for studying the processes of social change. However, a main difficulty in using this technique is to observe all relevant explanatory variables without missing any variables. This book presents a general approach to missing data problems in event history analysis which is based on the similarities between log-linear models, hazard models and event history models. It begins with a discussion of log-rate models, modified path models and methods for obtaining maximum likelihood estimates of the parameters of log-linear models. The author then shows how to incorporate variables with missing information in log-linear models - including latent class models, modified path models with latent variables and log-linear models for non-response. Other topics covered are: the main types of hazard models; censoring; the use of time-varying covariates; models for competing risks; multivariate hazard models; and a general approach for dealing with missing data problems - including measurement error in the dependent variable, measurement error in the covariates, partially missing information in the dependent variable and partially observed covariate values.