Sponsored by the Society for Epidemiologlc Research COMMENTARY Invited Commentary: Propensity Scores

The propensity score is the conditional probability of exposure to a treatment given observed covariates. In a cohort study, matching or stratifying treated and control subjects on a single variable, the propensity score, tends to balance all of the observed covariates; however, unlike random assignment of treatments, the propensity score may not also balance unobserved covariates. The authors review the uses and limitations of propensity scores and provide a brief outline of associated statistical theory. They also present a new result of using propensity scores in case-cohort studies. Am J Epidemiol 1999; 150:327-33. causality; confounding; observational study DEFINITION AND MOTIVATION An observational study is an attempt to estimate the effects of a treatment or an exposure by comparing out-comes for subjects who were not assigned at random to treatment or control, which would have happened in a randomized, controlled trial (1, 2). A variable, such as age or gender, that is measured prior to the start of treat-ment, and hence is unaffected by the treatment, will be called a covariate. Random assignment of subjects to treatment or control tends to balance covariates, so that treated and control groups are comparable in the sense that they have similar distributions of covariates, for instance, similar age distributions or similar propor-tions of women. Absent random assignment, the propensity score is a device for constructing matched pairs or matched sets or strata that balance numerous observed covariates (3). Adjustment for an estimated propensity score tends to balance observed covariates Received for publication February 3,1999, and accepted for pub