Modern Causal Inference and Treatment-Effect Estimation Using Stata
Half Day Short Course
9:00am – 1:00pm
This half-day workshop introduces participants to methods for analyzing causal relationships in observational (non-experimental) data. Covering both conceptual foundations and practical applications, the course presents a range of treatment-effect estimators for cross-sectional and panel data, with an emphasis on when and how each method should be used. Participants will engage with recent developments in causal inference through hands-on demonstrations using Stata software.
Topics include the estimation of average treatment effects (ATE), average treatment effects on the treated (ATET), and conditional average treatment effects (CATE), as well as techniques for estimating heterogeneous treatment effects through difference-in-differences (DID). Attendees will work through methods such as regression adjustment (RA), inverse-probability weighting (IPW), augmented IPW (AIPW), IPW regression adjustment, and treatment-effect lasso for high-dimensional data. Repeated cross-sectional and panel data methods, including DID and heterogeneous DID, will also be explored.
By the end of the session, participants will be able to use Stata to obtain causal inference parameters, interpret results, and run diagnostics to validate key model assumptions. This course is designed for anyone interested in advanced techniques in causal inference with a background in linear regression.
The workshop is led by Eduardo García Echeverri, Senior Econometrician at StataCorp LLC. Dr. García Echeverri holds a PhD in Economics from the University of Rochester and a master’s degree from Universidad de los Andes in Colombia. His research focuses on nonparametric and semiparametric econometric methods, and at Stata, he supports statistical feature development, documentation, and educational webinars.