A significant focus of modern empirical economics is causal inference. This chapter begins with a gentle introduction to the Neyman-Rubin potential outcomes causal model, which defines the causal effect of a treatment, and outlines the necessary assumptions for valid causal inference. We then explore matching techniques, a method applicable to observational data, in certain contexts. Since observational studies require careful adjustment for relevant regressors, matching helps achieve balance in the distribution of regressors between treated and control groups. Once balance is attained, we analyze the differences in outcomes between these groups. The chapter covers propensity score matching and genetic matching methods, demonstrating their application using data from a training program evaluation. Additionally, we illustrate the implementation of these methods using the Matching package in R programming language.