Reducing the Impact of Selection Bias with Propensity Scores
This intermediate-level workshop describes and demonstrates effective strategies for using propensity score methods to address the potential for selection bias in observational studies comparing exposures. We will review main analytical techniques associated with propensity score methods (multivariable adjustment, matching and stratification using the propensity score, sensitivity analysis) and describe key strategic concerns related to effective estimation of the propensity score, assessment and display of covariate balance, choice of analytic technique, sensitivity analyses for matched samples, and communicating results effectively to nonstatisticians. We also will review the literature regarding recent methodological advances in propensity scores and application of propensity score methods to problems in health policy research. Attendees will receive detailed handouts.