Causal mediation analysis in economics: Objectives, assumptions, models

Mediation analysis aims at identifying and evaluating the mechanisms through which treatment affects an outcome. The goal is to disentangle total effect into two components: indirect that occurs due one or more intermediate variables, known as mediators, direct captures all other possible explanations for why a works. This paper reviews methodological advancements in literature on causal mediation economics, specifically quasi-experimental designs. I define parameters of interest, main assumptions identification strategies under counterfactual approach, present Instrumental Variables (IV), Difference-in-Differences (DID), Synthetic Control (SC) methods.