Logistic Regression Analysis: Introduction and Applications

This applied workshop teaches participants how to use popular statistical software packages such as Stata, SPSS and R to conduct multivariate analyses of data of interest to social scientists and policy analysts. The course begins by reviewing the linear regression model and then focuses on important multivariate models for categorical data including binomial logit and probit models, multinomial logit models and the mixed logit model.  The workshop discusses how to present and interpret the results of analyses using these models, giving attention to the interpretation of interaction effects in linear and nonlinear models.

Example analyses using data gathered in national election surveys conducted by the instructor in Canada, Great Britain and the United States will be presented in class.  Participants also are invited to bring their own data sets to daily lab sessions.  There is no prerequisite for the course other than familiarity with basic statistics and an introduction to the OLS regression model.