matching

Note: This article demonstrates how to use propensity scores for matching data. However, propensity scores have come under fire in recent years. In their 2019 article, Why Propensity Scores Should Not Be Used for Matching, King and Nielsen argue that propensity scores increase imbalance, inefficiency, model dependence, and bias. Others argue that while propensity scores may be sub-optimal, they can be useful in certain situations.