| Autor: |
Rodríguez De Gil P; a University of South Florida., Bellara AP; a University of South Florida., Lanehart RE; a University of South Florida., Lee RS; a University of South Florida., Kim ES; a University of South Florida., Kromrey JD; a University of South Florida. |
| Jazyk: |
angličtina |
| Zdroj: |
Multivariate behavioral research [Multivariate Behav Res] 2015; Vol. 50 (5), pp. 520-32. Date of Electronic Publication: 2015 Jul 24. |
| DOI: |
10.1080/00273171.2015.1022643 |
| Abstrakt: |
Considering that the absence of measurement error in research is a rare phenomenon and its effects can be dramatic, we examine the impact of measurement error on propensity score (PS) analysis used to minimize selection bias in behavioral and social observational studies. A Monte Carlo study was conducted to explore the effects of measurement error on the treatment effect and balance estimates in PS analysis across seven different PS conditioning methods. In general, the results indicate that even low levels of measurement error in the covariates lead to substantial bias in estimates of treatment effects and concomitant reduction in confidence interval coverage across all methods of conditioning on the PS. |
| Databáze: |
MEDLINE |
| Externí odkaz: |
|
