An introduction to causal inference techniques used in empirical economic research, with emphasis on policy evaluation and impact assessment, this course is intended for students who have completed introductory econometrics and are ready to work with modern tools for uncovering causal relationships from observational and experimental data.

Beginning with the potential outcomes framework and the distinction between correlation and causation, the course covers quasi-experimental methods used to estimate causal effects when randomized control trials are not feasible: randomized experiments, matching methods, instrumental variables (IV), difference-in-differences (DiD), and regression discontinuity design (RDD). Each method is examined through its underlying assumptions, identification strategies, estimation techniques and threats to validity.

Students also develop the ability to critically assess empirical strategies in applied economic research and to implement these methods using Stata. Applications drawn from development economics, labor economics, public policy, and health economics illustrate the techniques throughout.