Variable selection for propensity score models when estimating treatment effects on multiple outcomes: a simulation study
Article first published online: 16 OCT 2012
Copyright © 2012 John Wiley & Sons, Ltd.
Pharmacoepidemiology and Drug Safety
Volume 22, Issue 1, pages 77–85, January 2013
How to Cite
Wyss, R., Girman, C. J., LoCasale, R. J., Alan Brookhart, M. and Stürmer, T. (2013), Variable selection for propensity score models when estimating treatment effects on multiple outcomes: a simulation study. Pharmacoepidem. Drug Safe., 22: 77–85. doi: 10.1002/pds.3356
- Issue published online: 7 JAN 2013
- Article first published online: 16 OCT 2012
- Manuscript Accepted: 18 SEP 2012
- Manuscript Revised: 13 SEP 2012
- Manuscript Received: 14 MAY 2012
- propensity scores;
- variable selection;
- instrumental variables;
It is often preferable to simplify the estimation of treatment effects on multiple outcomes by using a single propensity score (PS) model. Variable selection in PS models impacts the efficiency and validity of treatment effects. However, the impact of different variable selection strategies on the estimated treatment effects in settings involving multiple outcomes is not well understood. The authors use simulations to evaluate the impact of different variable selection strategies on the bias and precision of effect estimates to provide insight into the performance of various PS models in settings with multiple outcomes.
Simulated studies consisted of dichotomous treatment, two Poisson outcomes, and eight standard-normal covariates. Covariates were selected for the PS models based on their effects on treatment, a specific outcome, or both outcomes. The PSs were implemented using stratification, matching, and weighting (inverse probability treatment weighting).
PS models including only covariates affecting a specific outcome (outcome-specific models) resulted in the most efficient effect estimates. The PS model that only included covariates affecting either outcome (generic-outcome model) performed best among the models that simultaneously controlled measured confounding for both outcomes. Similar patterns were observed over the range of parameter values assessed and all PS implementation methods.
A single, generic-outcome model performed well compared with separate outcome-specific models in most scenarios considered. The results emphasize the benefit of using prior knowledge to identify covariates that affect the outcome when constructing PS models and support the potential to use a single, generic-outcome PS model when multiple outcomes are being examined. Copyright © 2012 John Wiley & Sons, Ltd.