Event Phone: 1-610-715-0115

Cancellation Policy: 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).

In the unlikely event that Statistical Horizons LLC must cancel a seminar, we will do our best to inform you as soon as possible of the cancellation. You would then have the option of receiving a full refund of the seminar fee or a credit towards another seminar. In no event shall Statistical Horizons LLC be liable for any incidental or consequential damages that you may incur because of the cancellation.

A 3-Day Livestream Seminar Taught by Shenyang Guo, Ph.D.

Propensity score analysis (PSA) is a modern, innovative class of statistical methods that has become increasingly valuable for evaluating the effects of treatments, programs, or interventions using nonexperimental or observational data. While regression analysis is commonly used to adjust for potentially confounding variables, PSA offers a compelling alternative.

For students and professionals across disciplines—including those in business, economics, public policy, health, and the social sciences—PSA provides a practical way to draw credible insights from real-world data. It is especially useful when randomized experiments are not feasible, such as when assessing the impact of a marketing campaign, policy change, or service rollout. Results from PSA are often easier to communicate to decision-makers and more robust to differences in the underlying characteristics of the groups being compared. Most importantly, PSA focuses on modeling the assignment to treatment without considering outcomes, ensuring the objectivity of the study design.

This seminar will cover the basics of implementing propensity score analysis, including how to use logistic regression and generalized boosted regression to estimate propensity scores, and how to apply these scores to perform propensity score matching and related models.

This seminar will focus on two methods to estimate propensity scores, and four methods to run corrective models of outcome analysis to enhance the study’s internal validity:

• Using logistic regression and generalized boosted regression to estimate the propensity scores.
• The classic matching methods, including nearest neighbor within caliper matching and Mahalanobis metric matching.
• The optimal matching methods.
• The inverse probability of treatment weights estimator, also known as propensity score weighting method.
• The Abadie and Imbens’s matching estimators.

The examination of these methods will be guided by the Neyman-Rubin counterfactual framework.