There is a long-standing debate about the extent to which economic theory should inform econometric modeling and estimation. This debate is particularly evident in the program/policy evaluation literature, where reduced-form (experimental or quasi-experimental) and structural modeling approaches are often viewed as rival methodologies. Reduced-form proponents criticize the assumptions invoked in structural applications. Structural modeling advocates point to the limitations of reduced-form approaches in not being able to inform about program impacts prior to implementation or about the costs and benefits of program designs that deviate from the one that was implemented. In this paper, we argue that there is a new emerging view of a natural synergy between these two approaches, that they can be melded to exploit the advantages and ameliorate the disadvantages of each. We provide examples of how data from randomized controlled trials (RCTs), the exemplar of reduced form practitioners, can be used to enhance the credibility of structural estimation. We also illustrate how the structural approach complements experimental analyses by enabling evaluation of counterfactual policies/programs. Lastly, we survey many recent studies that combine these methodologies in various ways across different subfields within economics.

The recent literature exploiting natural events as “natural experiment” instruments is reviewed to assess to what extent it has advanced empirical knowledge. A weakness of the studies that adopt this approach is that the necessary set of behavioral, market, and technological assumptions made by the authors in justifying their interpretations of the estimates is often absent. The methodology and findings from twenty studies are summarized and simple economic models are used to elucidate the implicit assumptions made by the authors and to demonstrate the sensitivity of the interpretations of the findings to the relaxation of some of these assumptions.