Recalling extra data: a replication study of Finding missing markets
3ie Replication Paper 5, 2015
In this study, Benjamin DK Wood and Michell Dong conduct an internal replication of Finding Missing Markets (and a Disturbing Epilogue): Evidence From an Export Crop Adoption and Marketing Intervention In Kenya (2009). The original impact evaluation, by Nava Ashraf, Xavier Giné and Dean Karlan, found that an agricultural commercialisation programme targeting new adopters was most effective at increasing smallholder farmer household income levels. The pure replication generally reproduces the original findings.
Wood and Dong examine the robustness of the results to both measurement and theory of change analysis. In doing so, the authors highlight the importance of accounting for the multiple rounds of original data collection and question the implicit theoretical reasoning behind the original heterogeneous outcomes analysis.
3ie also invites formal replies from the original authors. These are published on the 3ie website together with the replication study.