Treatment Effects Analysis

An On-Demand Seminar Taught by
Stephen Vaisey, Ph.D.

Read reviews of this seminar

To see a sample of the course materials, click here.

To watch a sample video, click here.

This seminar covers both the theory and practice of Treatment Effects Analysis — a family of techniques that include parametric and non-parametric forms of matching and weighting observational data to enable better causal inferences. The most commonly known technique in this family is propensity score matching. We will cover this technique, but you’ll soon see that propensity scores are just the tip of the iceberg; there are many, many more things you can do with your data to extract key insights.

The course takes place online in a series of four weekly installments of videos, quizzes, and assignments, and requires about 6-8 hours/week. You may participate at your own convenience; there are no set times when you are required to be online.

This four-week course can be accessed with any recent web browser on almost any platform, including iPhone, iPad, and Android devices. It consists of 12 modules:

  1. The Potential Outcomes Framework
  2. Computing Treatment Effects Manually
  3. Exact Matching
  4. Propensity Scores
  5. Propensity Score Matching
  6. Balancing Checking
  7. Inverse Probability Weighting
  8. Covariate Balancing Propensity Scores and Entropy Balancing
  9. Coarsened Exact Matching
  10. Doubly Robust Estimation
  11. Adding Regression Adjustment
  12. Loose Ends and Extensions

Each module consists of a video segment recorded from the remote 3-day version of the course. The modules contain all the lectures and slides from that course.

After each module there is a short multiple-choice quiz to test your knowledge. There are also  exercises in which you can apply what you’ve learned to a real data set. An online discussion forum is available for you to post questions or comments about any aspect of the course. All questions will be answered by Dr. Vaisey in a timely manner.


The goal of treatment-effects analysis is to identify the causal effect of a treatment on an outcome, such as the effect of a college education on earnings, the effect of divorce on child outcomes, or the effect of a training program on employee productivity. A major advantage of treatment-effects techniques over standard regression methods is that they can produce different estimates of causal effects for subjects who are likely to receive the treatment and for those who are unlikely to receive it, an important distinction for policy work.

This seminar will take participants from simple exact matching to recent developments like coarsened exact matching, doubly-robust estimators and entropy balancing. Participants will get extensive practical experience by working through case studies from economics, sociology, medicine, and public health.

We will cover a variety of topics including exact matching, propensity score matching and weighting, other forms of non-parametric matching and weighting, regression adjustment, and various forms of doubly-robust estimators. We will also consider tests for violations of assumptions and ways to test the sensitivity of results to violations of untestable assumptions. Although we will focus primarily on binary treatments, we will briefly explore how these techniques can be applied to multivalued treatments as well.


In the videos, Stata (Version 14 or higher) will be the main software package used to demonstrate the methods. Stata 13 can do at least 95% of what we will cover in this course. Some R will also be used to demonstrate techniques.

Participants who are not yet ready to purchase Stata could take advantage of StataCorp’s free 30-day evaluation offer or their 30-day software return policy. 

WHO SHOULD Register?

This course is for any who want to learn to apply this family of techniques to observational data. Participants should have a basic foundation in linear and logistic regression.

REVIEWS OF Treatment Effects Analysis

“Stephen Vaisey is a gifted instructor. He is both able to explain advanced concepts in a simple, clear manner and to make you laugh while he is doing it. This class is useful for any researcher who wants to improve their ability to make casual speculation with their research. I highly recommend this class and any that Stephen teaches.”
  Dennis Reidy, Georgia State University

“The course covered an extremely complex topic clearly and with a hands-on approach. I had taken a broader causal inference course before this, but I felt like this course really gave me the tools to conduct my own treatment effect analyses! Professor Vaisey was so good at making me think about these techniques through a research framework and how our research questions should really guide us towards what method to use.”
  Daniel Stephens, Truth Initiative

“I highly recommend this course. This is the second Statistical Horizons course I have taken. The first was on-site in Philadelphia a few years ago. It was a great course and I was very happy I took it. However, the online format is so much better. One gets the same lectures that are delivered on site, the same materials, given by the same top-rate instructors. The difference is that one can go through the materials at their own rate and take the time to process material before moving on to the next subject. Further, there is ample opportunity to interact with the instructor via email and the discussion forum. I am totally sold on this format and have already told Statistical Horizons to keep me updated about future online courses.”
  Bob Reed, University of Canterbury