In many educational intervention programs, it is not possible to randomly assign students to an experimental and control condition. For example, in our research we wanted to compare students who were enrolled in a biomedical pathway program to students who were not in such a program. However, students select their academic pathway program and a randomized controlled trial cannot be conducted. Propensity score matching (PSM) is a valuable statistical technique in areas of research when randomized control trials are not always possible. It can be widely used to mimic the process of randomization by creating comparable groups based on key covariates while increasing causal inference and reducing bias. The aim of this article is to provide guidance for science education researchers to make informed decisions about the selection of matching methods and implementation of PSM using the MatchIt package (Ho et al., 2011) in R. In this article, we 1) discuss the utility of using PSM for research involving educational interventions, 2) provide a comprehensive guide for conducting PSM with educational data and provide a detailed step-by-step guide on conducting PSM for nearest neighbor matching using R, and 3) apply it to a National Institutes of Health (NIH)-funded high school education program.