Discrete Choice Models in the Social Sciences
Tobias Böhmelt, University of Essex
21 July - 1 August (two week course / 35 hrs)
Tobias Böhmelt is a Lecturer in the Department of Government at the University of Essex and a Research Associate of the International Political Economy Group at the Center for Comparative and International Studies (CIS) as well as the Institute for Environmental Decisions (IED). His main research and teaching interests are the quantitative analysis of conflict and cooperation, environmental politics, international mediation, military effectiveness, and social network analysis.
- This course introduces the main techniques for analyzing models with discrete dependent variables. It begins with the basics of maximum likelihood estimation, a discussion of the theoretical foundations of discrete choice models, and then introduces logit and probit models. Afterwards, we cover interpretation and hypothesis testing with discrete choice models. Against this background, we consider more complicated discrete choice models, including ordered logits and probits, multinomial logits, count models, or discrete duration models. The course concludes with an overview of advanced techniques of discrete choice models with time-series cross-section data.
- this course, participants will be able to understand the discrete choice models most commonly used in the social sciences, and properly apply and interpret these models in their own work.
- Participants are assumed to have a background in probability theory and statistical inference, and a solid knowledge of multiple linear regression, including hands-on experience estimating regression models with statistical software. Some familiarity with linear algebra is assumed, but is not essential to success in the course.
Representative Background Reading
- Gujarati, Damodar N., and Dawn C. Porter. 2009. Essentials of Econometrics. Fourth Edition. New York: Irwin/McGraw-Hill.
- Wooldridge, Jeffrey M. 2008. Introductory Econometrics: A Modern Approach. Fourth Edition. Mason, OH: South-Western Cengage Learning.
- Train, Kenneth E. 2007. Discrete Choice Models with Simulation. Cambridge: Cambridge University Press.
- Please note this book will be provided by the Summer School on participants arrival
- Long, J. Scott. 1997. Regression Models for Categorical and Limited Dependent Variables. Thousand Oaks, CA: Sage Publications.