Propensity Score Matching

Thursday, June 1, 2017 - Friday, June 30, 2017

Download syllabus for this course.

Download the flyer for this course.

Course Description

This short course in Propensity Score Matching will introduce students to causal inference in public health and epidemiology, focusing on the counterfactual framework and the method of propensity score matching. Students will conduct analyses on actual datasets using STATA (additional syntax for corresponding analysis in SPSS and SAS will be provided). The course will cover basics of propensity score matching including estimation of propensity scores and selection of covariates, matching methods, and post-matching multivariate analyses.

Course Objectives


By the end of the course, participants will be able to:

  1. Describe the tenants of causal inference and the counterfactual framework
  2. Understand the differences between experimental, quasiexperimental, and nonexperimental research designs
  3. Read data into STATA and estimate propensity scores to represent probability of treatment assignment, conditional on included covariates
  4. Select appropriate covariates to estimate propensity scores
  5. Implement a variety of matching algorithms in STATA using psmatch2 and default treatment effect modules
  6. Evaluate post-match differences in treatment and control groups
  7. Graphically illustrate the region of common support
  8. Conduct post-matching multivariate analyses to evaluate average treatment effects




Students should be familiar with multiple logistic regression. No familiarity is assumed with causal inference. Prior experience with STATA is not required but will be beneficial for ease of use; however, all presented analyses and demonstrations can be replicated without prior knowledge of STATA. Students will need access to a computer with high-speed internet access and STATA (version 13 or higher).


Course Reading List


There are no required readings, however we strongly recommend the following three references. The first is a gentle introduction to PSM and observational research; the second is an applied example with greater mathematical sophistication; the third is a primer for non-Stata users.

  1. Austin PC. An introduction to propensity score methods for reducing the effects of confounding in observational studies. Multivariate Behavioral Research, June 2011. ?
  2. Dehejia RH, Wahba S. Propensity score matching methods for nonexperimental causal studies. The Review of Economics and Statistics, 2002, 84(1): 151-161.
  3. Introduction to Stata (Chapters 1-4):



Ryan Richard Ruff, MPH, PhD

Dr. Ryan Richard Ruff is an Assistant Professor of Epidemiology and Health Promotion at the New York University College of Dentistry and the New York University College of Global Public Health. His research focuses on the relationship between oral health and child development, specifically quality of life, psychosocial functioning, and educational performance. He is particularly interested in the causal effects of school-based caries prevention and the trends in socioemotional development in children with cleft lip and palate. He is the Director of the Biostatisics Core and Director of the MS Program in Clinical Research at the NYU College of Dentistry. Dr. Ruff received his PhD in Research, Statistics, and Evaluation from the University of Virginia, his MPH in Epidemiology from Harvard, and his MPhil in Education from Cambridge.

Course Fee

Registration is $200.00

DISCOUNT of 10% will be applied at checkout for all registrations on or before April 1st.


The registration period has closed for this event.

Online Course Format

This is a short digital course, equivalent to approximately 5 hours of classroom instruction. Lectures and course material will be presented online. The flexible format will include video or audio recordings of lecture material, file sharing and topical discussion fora, self-assessment exercises, real-time electronic office hours and access to instructors for feedback during the course. Registrants for EPIC digital courses should have high-speed internet access. Any additional information about technical requirements and access to the course will be provided the month before the course begins.

Share This