Quality evidence for policymaking: I'll believe it when I see the replication

In this paper, we make the case for replication as a crucial methodology for validating research used for evidence-based policymaking, especially in low- and middle-income countries. We focus on internal replication or the reanalysis of original data to address an original evaluation or research question. We review the current state of replication in the social sciences and present data on the trends among academic publications. We then discuss four challenges facing empirical research that internal replication can help to address. We offer a new typology of replication approaches for addressing these challenges. The types - pure replication, measurement and estimation analysis, and theory of change analysis - highlight that internal replication can test for consistency and statistical robustness but can and should also be used to ensure that a study fully explores possible theories of change in order to draw appropriate conclusions and recommendations for policymaking and programme design.