Date:
Location:
Our upcoming event for the Statistics Department Colloquium Series is scheduled for Monday, November 13 from 12:00 – 1:00pm (ET) and will be an in-person presentation Science Center Rm. 316. Lunch will be provided to guests following the talk. This week's speaker will be Davide Viviano of the Economics Department at Harvard University.
Title: Policy design in experiments with network interference
Abstract: One of the goals of a government or NGO is to estimate the welfare-maximizing policy. Network interference is often a challenge: treating an individual may also generate spillovers and affect the design of the optimal policy.
In this talk, I discuss methods for the estimation of treatment effects and welfare-maximizing treatment allocation rules in the presence of spillover effects. First, I introduce a method that maximizes the sample analog of average social welfare when spillovers occur using information from a (quasi)experiment. I construct semi-parametric welfare estimators with known and unknown propensity scores and cast the optimization problem into a mixed-integer linear program. I derive a strong set of guarantees on regret, i.e., the difference between the maximum attainable welfare and the welfare evaluated at the estimated policy. Second, I present methods for experimental design in the presence of spillover effects and illustrate their applicability in a large-scale experiment on information diffusion on social networks.
Bio: Davide Viviano is a postdoctoral fellow and assistant professor starting next year at the Department of Economics at Harvard. His research combines economics and statistics to develop or justify methods for applications in social sciences, with a focus on policy design and causal inference. Prior to joining Harvard, he was a postdoctoral fellow at Stanford GSB and received his PhD in economics from UC San Diego.