‘Propensity scores’ in observationeel onderzoek

Conflict of interest: none declared. Financial support: none declared.

• A propensity score is the probability of being treated or exposed, given measured confounders such as age.

• Propensity score methods can control for measured confounders in observational research, but not for unmeasured confounders.

• Study participants with the same propensity score will, on average, have a similar distribution of measured confounders.

• The propensity score can be used to control for confounding by means of stratification, matching, including the propensity score as a covariate in a multivariable regression model, or by weighting the study population using the propensity score.

• Propensity score methods can often control for more confounders than other methods, particularly in the case of a rare outcome.

• Reports on propensity score methods should mention which confounders were included in the propensity score and to what extent confounders were balanced across study groups, after stratification based on the propensity score.