Transparency, Replication, and Cumulative Learning: What Experiments Alone Cannot Achieve

Replication of simple and transparent experiments should promote the cumulation of knowledge. Yet, randomization alone does not guarantee simple analysis, transparent reporting, or third-party replication. This article surveys several challenges to cumulative learning from experiments and discusses emerging research practices—including several kinds of prespecification, two forms of replication, and a new model for coordinated experimental research—that may partially overcome the obstacles. I reflect on both the strengths and limitations of these new approaches to doing social science research. NOTE: This article has been corrected and republished as doi:10.1146/annurev-polisci-072516-014127.