- Browse
Search
Program Calendar
Browse By Day
Browse By Time
Browse By Person
Browse By Room
Browse By Unit
Browse By Session Type
- Information Menu
Search Tips
Visiting Washington, D.C.
- Navigation and Settings Menu
Personal Schedule
Sign In
- Social Media Menu
Facebook
X (Twitter)
Examining Discrepancies in Propensity Score Matching Results From Various Software Packages for Evaluation Research
Sat, April 9, 2:15 to 3:45pm, Convention Center, Floor: Level Two, Exhibit Hall DSession Type: Poster Session
Abstract
Evaluation researchers have increasingly used propensity score matching (PSM) in evaluation research to estimate treatment effects. PSM results directly affect the estimation of treatment effects. There are a few studies focusing on the comparison of results from various PSM techniques using the same software package, but the issue of inconsistent results from the same PSM technique using various software packages has not been fully understood. The current study aims to examine the discrepancies in PSM results from various software packages such as in R, SAS, Stata, and SPSS. This study will help evaluation researchers understand the constraints and consequences of various software packages when using PSM for advancing their evaluation research.