P Aronow @ Yale
Abstract:
I present a design-based framework for estimating causal effects in randomized experiments performed on networks. I discuss high-level conditions for the unbiasedness and root-n consistency of inverse-probability-weighted estimators as well as a basis for asymptotic inference. This framework is applied to a large-scale schools-based randomized experiment that includes comprehensive social network measurement.
Bio:
P Aronow is Associate Professor of Political Science, Biostatistics, and Statistics and Data Science at Yale University. P works on a wide variety of topics, including causal inference, networks, high-dimensional statistics, machine learning, econometrics, metascience, and applied social science. They have published in the top journals of multiple disciplines and authored a popular graduate-level textbook, Foundations of Agnostic Statistics (Cambridge UP, 2019). They received their BEng from Cooper Union in 2008, and their PhD from Yale in 2013.