Categorical Data Analysis in Stata

Instructor(s):

• J. Scott Long, Sociology, Indiana University

This workshop examines the most important regression models for binary,ordinal, nominal, and count outcomes. The goal of this class is to teach participants how to estimate and interpret these models.

The first two days are used used to presenting fundamental issues of estimation, testing and assessing fit of nonlinear models and to introduce how Stata can be used to easily estimate and interpret these models. Basic concepts and notation are introduced by reviewing the linear regression model. Within this familiar context, the method of maximum likelihood estimation is presented. These ideas are then used to explain the logit and probit models for binary outcomes. The focus is on using numerical and graphical methods to effectively interpret these models. Statistical testing and assessing fit are also illustrated using real-world examples.

The last three days consider models for nominal, ordinal, and count outcomes. The ordinal model is presented as a series of binary models that are simultaneously estimated with constraints. This allows methods of testing and interpretation the binary model to be easily extended to ordinal models. Next, the multinomial logit model is presented. While conceptually this model is a simple extension of binary logit, the large number of parameters in the model can made this model difficult to interpret. Graphical methods are introduced to address this difficulty, along with a series of particularly useful statistical tests. The last day deals with models for count outcomes, including Poisson regression, negative binomial regression, and zero modified models. Participants should be familiar with linear regression.

NOTE: the course, itself, will run from Monday, June 15 through Friday, June 19. In addition, there will be an optional "Introduction to Stata" session that will be held before the class begins, on Sunday afternoon, June 14. This session is intended for non-Stata users. For course participants who cannot make the Sunday session, sufficient information for getting started with Stata will be provided in class.

Dates:  June 15-19 

Fee:  Member: $1800; Non-member: $4000

This course is limited to 20 participants.