Statistical Models for Causal Analysis.

Abstract

This book provides a quick overview of statistical models commonly used in causal analyses of nonexperimental data in the social and biomedical sciences. Topics covered are simple bivariate regression multiple regression multiple classification analysis path analysis logit regression multinomial logit regression and survival models (proportional hazard models and hazard models with time dependence). The methods described are illustrated using data from the 1974 Fiji Fertility Survey conducted as part of the World Fertility Survey. (EXCERPT)