This class will cover the key issues of endogeneity and Instrumental Variable estimation:

1. Introduction & Terminology

2. How Instrumental Variables tackle endogeneity

3. Choice of Instruments (Strength; Validity; Examples)

4. Multiple endogenous regressors, quadratic effects & interactions

5. Binary endogenous regressors

6. Control function & holdout sample validation

     7. IV-Free methods

Many empirical research projects that use non-experimental data are struggling with the proper identification of causal effects of independent variables (e.g., price, advertising) on dependent variables (e.g., sales). The reason is that the identification of a causal effect hinges on an untestable assumption that the error term of a model is uncorrelated with the independent variables. If this assumption is not met, a model is plagued by endogeneity.

The topic of endogeneity has received considerable attention and is probably the most frequently encountered troublemaker in a review process at an academic journal.

This course therefore has the goal of making students familiar with the problem of endogeneity and potential remedies. Because the literature on endogeneity is often quite technical, this course aims at providing an easily accessible approach to this topic.

Every student who wishes to earn credits will(a) briefly (15 minutes) present an outline of a research project that is partof the PhD thesis and that deals with the identification of a causal effect oris affected by endogeneity, or (b) briefly (15 minutes) present one researchpaper from the reading list, which will be distributed to participants inadvance. In both cases, students must submit a pdf of their presentation slidesafter class.

Further, students are expected to activelyparticipate in class and contribute to discussions.

Students participating in this course should have a solid knowledge of regression analysis and the underlying assumptions. Students should have some experience with actually applying regression analysis. This class is not a substitute for a full econometric education.

Contact: Dr. Nils Wlömert; nils.wloemert@wu.ac.at; +43 1 31 336 4958

The lecture is held by visiting professor Dominik Papies from University of Tübingen [Link]