Causal Inference

In this blog post, I use Gelman and Loken’s garden of forking paths analysis to construct a simulation showing why skepticism of AstraZeneca’s vaccine results is warranted at this early stage.

Background Conjoint survey experiments have become more popular in political science since the publication of Hainmueller, Hopkins and Yamamoto (2014). However, analysis of the statistical of power of conjoint experiments is difficult using standard parametric techniques because of the use of multiple treatments, interaction effects and paired vignettes.