The propensity score is the conditional probability of exposure to a treatm
ent given observed covariates. In a cohort study, matching or stratifying t
reated and control subjects on a single variable, the propensity score, ten
ds to balance all of the observed covariates; however, unlike random assign
ment of treatments, the propensity score may not also balance unobserved co
variates. The authors review the uses and limitations of propensity scores
and provide a brief outline of associated statistical theory. They also pre
sent a new result of using propensity scores in case-cohort studies.