Many fields of science are faced with the inability to perform randomized experiments, but wish to have the ability to estimate a treatment effect and make causal inference. Propensity score matching is a method that can be used in observational studies to obtain unbiased estimates of the treatment effect. In this paper we consider the theory behind utilizing propensity score
matching to obtain these such estimates, as well as explain how to implement propensity score matching in R using the Matching package for data from Montana State University’s Introductory Statistics curriculum.
