· Daniel Millimet summarizes the Andrews and Armstrong IV estimator (which has Stata code aaniv) – this deals with the issue that the standard IV estimator, while consistent, is not unbiased. Andrews and Armstrong show that if you know the sign of the first stage relationship, then you can obtain an unbiased estimate. This should be particularly useful for estimating the TOT in a RCT, since you know that assignment to treatment should increase the likelihood of being treated.
· Forget nightlights and satellite imagery for poverty mapping, just look in the sewers! The Economist on how wastewater provides clues of socioeconomic status.
· JPAL has launched a new library of research resources, with practical resources on different aspects of the lifecycle of running a field experiment. It is nicely structured, with sections for each stage of designing and setting up and running a study.
· The latest SIEF From Evidence to Policy note summarizes the impact of one additional year of pre-school in Bangladesh
· On the LSE blog, Ryan Jablonski, Brigitte Seim and Johan Ahlback summarize their forthcoming JDE paper that looks at fungibility of aid and whether aid crowds out other spending on education. “We asked 460 sitting MPs and councilors in Malawi to make a series of real decisions about the allocation of education supplies to schools in their constituencies. Before they made these decisions, we randomly provided some of the politicians with information about foreign aid projects at these schools. We then compared politicians’ allocation decisions in an environment where they learned, or not, about foreign aid in their communities….Our most credible estimates suggest a politician who learns about foreign aid is 22–29% less likely to spend anything in a school with a foreign aid project”
Join the Conversation