|
Abstract:
|
Propensity score methods (PSMs) have become a common practice in observational studies to reduce selection bias. However, researchers still often encounter in-depth methodological challenges in practice. For example, how to check assumptions? How to select covariates? How to deal with multiple treatments? How to deal with complex data such as clustered, longitudinal, or survey data? How to conduct outcome analysis with PSMs? How to conduct sensitivity analysis after applying PSMs? This course will build upon the fundamental principle and concept of PSMs to tackle these in-depth methodological challenges along with relevant R packages, such as hdPS, twang, Zelig, and rbounds. Through lectures on the advanced topics in PSMs and hands-on activities for using the R packages, this course will help researchers better understand PSMs and, therefore, improve the validity of their observational studies. Instructions for downloading and installing the R packages with examples of real-world data will be provided to participants in advance through a course website. A working knowledge of PSMs is required. Participants are encouraged to bring their own computers for hands-on activities on the data provided in the course, and they are also welcomed to work on their own real-world data.
|
