Propensity Score Analysis
A 2-Day Seminar Taught by Shenyang Guo, Ph.D.
To view a sample of the course materials, click here.
Propensity score analysis is a relatively new and innovative class of statistical methods that has proven useful for evaluating the effects of treatments or interventions when using nonexperimental or observational data. Although regression analysis is most often used to adjust for potentially confounding variables, propensity score analysis is an attractive alternative. Results produced by propensity score methods are typically easier to communicate to lay audiences. And propensity score estimates are often more robust to differences in the distributions of the confounding variables across the groups being compared. This seminar will focus on three closely related but technically distinct propensity score methods:
- Propensity score matching and related methods, including greedy matching, optimal matching, and propensity score weighting using Stata psmatch2, pweights and R optmatch
- Matching estimators using Stata nnmatch
- Propensity score analysis with nonparametric regression using Stata psmatch2 and lowess.
The examination of these methods will be guided by two conceptual frameworks: the Neyman-Rubin counterfactual framework and the Heckman scientific model of causality. The course also covers Rosenbaum’s approaches of sensitivity analysis to discern bias produced by hidden selections. The seminar uses Stata software to demonstrate the implementation of propensity score analysis. All syntax files and illustrative data can be downloaded at the Propensity Score Analysis Support Site.
Who should attend
The seminar will be helpful to researchers who are engaged in intervention research, program evaluation, or more generally causal inference, when their data were not generated by a randomized clinical trial. The prerequisite for taking this seminar is knowledge of multiple regression analysis. Researchers from economics, public health, epidemiology, psychology, sociology, social work, medical research, education, and similar disciplines may consider participating.
LOCATION, Format, and MATERIALS
The class will meet from 9 am to 4 pm each day with a 1-hour lunch break at DePaul Center, Loop Campus, 1 East Jackson Boulevard, Chicago, IL 60604.
Participants receive a bound manual containing detailed lecture notes (with equations and graphics), examples of computer printout, and many other useful features. This book frees participants from the distracting task of note taking.
Registration and lodging
The fee of $995 includes all course materials.
If you cancel your registration at least two weeks before the course is scheduled to begin, you are entitled to a full refund (minus a processing fee of $50).
Lodging Reservation Instructions
A block of guest rooms has been reserved at The Congress Plaza Hotel, 520 South Michigan Avenue, Chicago, IL 60605. In order to make reservations, call 312-427-3800 Ext. 5025 and identify yourself as part of the Statistical Horizons group or click here for a special rate of $119. For guaranteed rate and availability, you must reserve your room no later than Tuesday, October 10.
- Observational studies and outlines
- Why and when propensity score analysis is needed
- The Neyman-Rubin counterfactual framework
- The assumption of strongly ignorable treatment assignment
- The stable unit treatment value assumption
- Truncation, censoring, and incidental truncation
- The Rosenbaum and Rubin model (1983)
- Greedy matching; Stata-psmatch2
- Optimal matching; R-optmatch
- Post-optimal-matching analysis
- Propensity score weighting
- Matching estimators; Stata-nnmatch
- The kernel-based matching estimator; Stata-psmatch2
- Rosenbaum’s sensitivity analysis; Stata-rbounds
- Overview of Heckman’s model of causality
- Criticism of nonexperimental approaches
- Directions of future development
“Dr Guo covered classical and new approaches in PSA with hands-on data and syntax as well as the theoretical underpinnings. After this course, I feel confident in applying this method to my own research.”
Sangmi Kim, Augusta University, Georgia Cancer Center
“This course really helped to solidify my propensity score matching approach and provided robust methods to handle complex problems we face everyday with our data.”
Alyce Anderson, University of Pittsburgh
“This was a great course, and I would recommend it to anyone thinking about using propensity score matching. Dr. Guo is clearly very knowledgeable on all aspects of this method.”
Richard Stringer, Old Dominion University
“This is an excellent course offered by a professor that clearly has a thorough mastery of the material. I’m looking forward to the challenge of applying what I’ve learned to my own data sets. I highly recommend the course.”
Chris Morris, University of Florida
“This class was great. Dr. Guo made sure to answer everyone’s questions and was enthusiastic about the material. He was very approachable and helped to make the class feel less overwhelming. The other great thing about this was that he used real world examples, so that students could learn how to apply these techniques and included syntax notes, which is very helpful to students who are new to Stata. I would highly recommend this course to anyone who needs a better understanding of Propensity Score Analysis.”
Kelsey Thiem, University of Massachusetts
“The course helped explained the various approaches available to balance observed data and helped underscore the importance of testing multiple models as a check on the robustness of findings (rather than choosing the easiest approach). The course gives you the tools to know which models to choose, under which circumstances, depending on your data (size and nature of your outcome variable). I definitely feel that it helped make the content from the book to finally “click”.”
Sarah Manchak, University of Cincinnati