UC San Diego

This dissertation presents three essays in the design of randomized experiments in economics. Chapter 1 "Testing for Underpowered Literatures" proposes a novel estimator consistent for the expected number of statistically significant results that a set of experiments would have reported had their sample sizes all been counterfactually increased by a chosen factor. An application to randomized controlled trials (RCTs) published in top economics journals finds that doubling every experiment’s sample size would only increase the power of two-sided t-tests by 7.2 percentage points on average. Chapter 2 "Linear Estimation of Global Average Treatment Effects" studies the problem of estimating the average causal effect of treating every member of a population, as opposed to none, using an experiment that treats only some. We provide recommendations for experimental designs and estimation procedures. Chapter 3 "Evaluation of a Teacher Training in Uganda: Specifications for Endline" is a midline report for a multi-year field experiment in Uganda. The experiment evaluates the impact of a general skills teacher training program in rural Uganda. In the trial, we offer the program to a sample of 640 teachers in 39 secondary schools. The chapter describes data collected so far, proposes hypotheses and estimands for endline, and demonstrates the precision of these methods by running them on midline data.