Causal Inference with Social Network Data by Prof. Duncan Clark, Williams College

Causal Inference with Social Network Data by Prof. Duncan Clark, Williams College, Wednesday October 2, 1:00 – 1:50pm, NSB 015, Wachenheim, Statistics Colloquium

This talk focuses on a method to derive causal inference in the setting of a social network. For example, the effect of having 1 more friendship in a network, on some outcome of interest. Claiming causal inferences in this setting requires careful consideration of the often complex dependency between outcomes for actors. Of particular importance are treatment spillover or outcome interference effects. I consider a model for causality when the underlying network is endogenous; where the ties between actors and the actor covariates are statistically dependent. I develop a joint model for the relational and covariate generating process that avoids restrictive separability and fixed network assumptions, as these rarely hold in realistic social settings. I will present potential outcome based inference within a Bayesian framework, demonstrating the value of the framework in a case-study of smoking in the context of adolescent friendship networks.