Home  /  Learn  /  Web training  /  Causal inference using Stata: Estimating average treatment effects

Causal inference using Stata: Estimating average treatment effects

4 days 3–4 hours daily

Learn how to use Stata’s treatment-effects estimators to estimate the effect caused by getting one treatment instead of another in observational data. We will discuss how observational data differ from experimental data and use the potential-outcomes framework to obtain the average treatment effect and the average treatment effect on the treated using a variety of estimators, including those suitable for endogenously assigned treatment. We will cover the conceptual and theoretical underpinnings of treatment effects as well as many examples using Stata.

← Back to all courses

Upcoming sessions

Currently, there are no scheduled sessions of this course.

Course leader

Alvaro Fuentes Higuera portrait

Alvaro Fuentes Higuera

Senior Econometrician

Alvaro Fuentes Higuera is a Senior Econometrician at StataCorp LLC. His PhD research at the Leibniz Institute for Science and Mathematics Education in Kiel, Germany, focused on propensity-score methods for causal inference with multilevel data. At Stata, he produces documentation and other written materials and develops and presents trainings.

Prerequisite

  • A general familiarity with Stata and a graduate-level course in regression analysis or comparable experience.

Course topics

  • Treatment-effects estimators

    • Regression-adjustment estimator
    • Inverse-probability-weighting (IPW) estimator
    • Augmented IPW estimator
    • IPW regression-adjustment estimator
    • Nearest-neighbor matching estimator
    • Propensity-score matching estimator
    • Treatment-effects estimation using lasso
    • Difference-in-differences estimation
    • Causal forests and treatment-effect heterogeneity

  • Endogenous treatment effects within the potential-outcome framework


  • The double-robustness property of the augmented IPW and IPW regression-adjustment estimators


  • Using different functional forms for the outcome model and treatment model

Future sessions

Inform me when the next session is available.




 

I would like to receive the following email alerts:

*Select all that apply

To ensure delivery of emails to your inbox, add [email protected] to your address book.