An Introduction to Alternative Methods in Program Impact Evaluation

During the recent years, researchers as well as policy makers have been increasingly interested in impact evaluation of development programs. A large number of impact evaluations have been developed and applied to measure the impact of programs. Different impact evaluation methods rely on different identification assumptions. This paper presents an overview of several widely-used methods in program impact evaluation. In addition to a randomization-based method, these methods are categorized into: (i) methods assuming 'selection on observable' and (ii) methods assuming 'selection on unobservable'. The paper discusses each method under identification assumptions and estimation strategy. Identification assumptions are presented in a unified framework of counterfactual and two-equation model.