The porous dialectic: Experimental and non-experimental methods in development economics

This paper provides a survey of six widely used non-experimental methods for estimating the impact of programmes in the context of developing economies (instrumental variables, regression discontinuity, direct matching, propensity score matching, linear regression and non-parametric methods, and difference-in-differences), and assesses their internal and external validity relative both to each other and to randomized controlled trials. While randomized controlled trials can achieve the highest degree of internal validity when cleanly implemented in the field, the availability of large, nationally representative datasets offers the opportunity for a high degree of external validity using non-experimental methods. Whereas these methods are often presented as competing alternatives, we argue that each method has merits in some context and that experimental and non-experimental methods are complements rather than substitutes.