Applied Empirical Modeling of Nonlinearity and Endogeneity in Regression Models (SoSe 2026)
Notice
The course is taught by Prof. Dr. Richard T. Gretz (University of Texas at San Antonio).
Course dates: 9–10 April and 13–14 April 2026.
The course takes place in room 006, Marketing Center Münster (MCM).
Additional course information (including the complete syllabus, slides, datasets, and Stata code) will be made available to participants via Learnweb. The enrollment passphrase will be sent to registered participants by e-mail.
If you are interested in participating, please send your registration to Tanja Geringhoff (Tanja.Geringhoff@wiwi.uni-muenster.de; including your full name, department, date of birth, PO, and student id) and any questions regarding the course to Philo Freiboth (philo.freiboth@wiwi.uni-muenster.de).
Information for all PhD students: The course counts as an A certificate for the PhD program.
Information for students of the Minor Research: If your application was successful, please register at the examination office for the early examination period. The examination modalities will be published here once they have been finalized.
Description
Often, empirical research problems do not fit the assumptions underlying Ordinary Least Squares (OLS) estimation. Applied researchers frequently encounter endogeneity, nonlinear relationships among regressors, and data structures involving repeated observations over time or across units. This workshop focuses on three core challenges commonly faced in applied empirical work: (1) endogeneity and instrumental variable methods, (2) nonlinearities on the right-hand side of regression models, and (3) panel data analysis. Each topic is motivated by practical empirical problems rather than abstract econometric theory. The course begins with an in-depth treatment of endogeneity, including its sources, consequences for estimation, and strategies for identification using instrumental variables. We then turn to nonlinearities in independent variables, with a focus on interaction effects, marginal effects, and interpretation challenges in regression models. Finally, the workshop introduces panel data methods, covering fixed effects, random effects, and related extensions. By the end of the workshop, participants should be able to understand and implement a range of applied econometric models using Stata, including instrumental variable estimation and diagnostics, models with interaction effects and nonlinearities, and panel data models addressing unobserved heterogeneity and selection concerns.
Lecturers
- Univ.-Prof. Dr. Thorsten Hennig-Thurau (responsible)
- Philo Freiboth (accompanying)