Online Program
Saturday, February 21 | |
PS3 Poster Session 3 & Continental Breakfast |
Sat, Feb 21, 8:00 AM - 9:15 AM
Napoleon AB |
An Empirical Investigation of the Impact of Measurement Error on Propensity Score Analysis (303049)Aarti P. Bellara, University of South FloridaEun Sook Kim, University of South Florida Jeffrey D. Kromrey, University of South Florida Rheta E. Lanehart, University of South Florida Reginald Lee, University of South Florida *Patricia Rodríguez de Gil, University of South Florida Keywords: propensity score, measurement error, simulation The absence of measurement error in research is a rare phenomenon. In the area of propensity score analysis, which is implemented to minimize the effects of selection bias in quasi-experimental studies, the impact of fallible covariates can be severe. Using a Monte Carlo approach, this study investigated the effect of measurement error on the estimation of treatment effects and balance estimates in propensity score analysis across seven propensity score methods. In general, results indicate that even low levels of measurement error in the covariates lead to substantial statistical bias in estimates of treatment effects and reduction in confidence interval coverage across all methods of conditioning on the propensity score.
|