Blavatnik School of Government, University of Oxford
The latest post on both the World Bank's Development Impact Blog and on the Berkeley Initiative for Transparency in the Social Sciences blog features Owen Ozier and RISE team members Clare Leaver, Pieter Serneels, and Andrew Zeitlin.
The holiday-themed blog, Power to the Plan, sets out a “recipe” for creating a pre-analysis plan with blinded endline data. The authors illustrate what can be learned from this recipe using examples from their recent experiment that tests the recruitment, effort, and retention consequences of pay-for-performance schemes in Rwandan education. These examples show that pre-analytical work using blinded endline data can be a useful tool to make informed choices of models and test statistics that improve power. In some situations, the right choice of test statistic can quadruple statistical power or better.
The full blog can be read on the World Bank's Development Impact website or on the BITSS blog.
RISE blog posts and podcasts reflect the views of the authors and do not necessarily represent the views of the organisation or our funders.