CATEGORICAL DATA ANALYSIS USING STATA: Models for Binary, Ordinal, Nominal, and Count Outcomes
<p>Dr. Simon Cheng, Associate Professor of Sociology from the University of Connecticut</p>
The workshop deals with the most important regression models for binary, ordinal, nominal and count outcomes. While advances in software make it simple to estimate these models, post-estimation interpretation is difficult due to the nonlinearities. The workshop begins by considering the general objectives for interpreting results from any regression model and then considers why achieving these objectives is more difficult when models are nonlinear. Basic concepts and notation are introduced in a quick review of the linear regression model. Maximum likelihood estimation and identification are also introduced. These ideas are used to develop the binary logit and probit models. For these models, numerous methods of interpretation are examined. The methods of estimation and interpretation for binary outcomes are extended to ordinal outcomes using the ordinal logit and probit models. The multinomial logit model for nominal outcomes is then discussed. Finally, a series of models for count data, including Poisson regression, negative binomial regression, and zero modified models are presented.