400017 SE Causality in Quantitative Research (2024S)

This course provides an overview of how causality is conceptualized and understood in quantitative research in the social sciences, focusing on the theoretical assumptions underlying popular research designs and methods for causal inference. After a quick review of different conceptions of causality, we introduce and focus on Neyman and Rubin's "potential outcomes framework" that has achieved a dominant position of how quantitative researchers think about causality in the social sciences. We then survey five different classes of popular research designs and methods for causal inference that are based on the potential outcomes framework:

1) Matching methods
2) Instrumental variables
3) Difference-in-differences
4) Synthetic control
5) Regression discontinuity designs

These methods rely on different sets of identifying assumptions to correct for selection bias on observables and unobservables that impede causal inference. With regard to each approach covered, we will work out and discuss its theoretical foundations and assumptions, consider its practical challenges, critically discuss its application in published works as well as practice the interpretation of its results.
Some basic understanding of quantitative research methods (e.g. multiple regression analysis) is desired, but students with strong motivation may also acquire this knowledge in parallel to the course. Students should also note that the materials will involve formulas and equations.