11.018 - PDC09: Propensity Score Methods and Their Applications in Observational Studies

Session Type: Professional Development Course

Abstract

Observational studies pose threats to the validity of treatment effect estimation due to selection bias. Propensity score methods have been increasingly used as a means of reducing selection bias so as to approximate the characteristics of experimental designs. This course will introduce concepts and issues related to propensity score methods, including matching, stratification, and weighting, and will also discuss when and how to use propensity score methods in observational studies using real-world examples with large-scale, national survey data. Lectures on theory and hands-on activities with statistical software in R and Stata will benefit faculty members, graduate students, and applied researchers in improving the quality of observational studies. Instructions for downloading and installing related statistical software and example data will be provided to participants in advance through a course website. No prior knowledge of propensity score methods is required. However, an understanding of research design and basic statistics, such as t-tests and regression, is preferable. Participants are advised to bring their own laptop computers for hands-on activities.

Sub Unit

• Professional Development and Training Committee

Instructors

• Haiyan Bai, University of Central Florida

• Wei Pan, Duke University

• Christopher M. Swoboda, University of Cincinnati