Edo Airoldi, Associate Professor of Statistics at Harvard University
A number of scientific endeavors of current national and international interest involve populations with interacting and/or interfering units. In these problems, measurements about interactions and interference (e.g., social structure and familial relations) are available, in addition to traditional measurements about unit-level outcomes and covariates. Formal statistical models for the analysis of this type of data have emerged as a major topic of interest in diverse areas of science. In this talk, Airoldi will review a few ideas and open research problems that are central to this burgeoning literature, placing emphasis on inference and other core statistical issues. Then he will turn to describe: (1) a new notion of non-ignorability that applies to network sampling designs, (2) an inference strategy that can be used to obtain valid estimates in these settings, and (3) a strategy to extend the Neyman-Rubin framework for estimating causal effects in the presence of social interference. Airoldi will illustrate these methods with applications to marketing on social media platforms in which these statistical problems arise.