Propensity Score
In causal inference, the conditional probability that an individual receives a specific treatment based on their observed background characteristics.
Think of It Like This
Like calculating the likelihood that a patient would have chosen to take a new experimental drug based purely on their age, weight, and prior medical history.
Propensity scores are used to correct for selection bias in observational studies where true randomized control trials are impossible. By matching or weighting individuals with similar propensity scores, researchers can isolate the true causal effect of a treatment. This allows analysts to simulate a randomized experiment from messy historical data.