Causal Inference Under Network Interference with Noise

• Activity Number: 80 - Graphical Models and Causal Inference
• Type: Contributed
• Date/Time: Sunday, July 28, 2019 : 4:00 PM to 5:50 PM
• Sponsor: Section on Statistical Learning and Data Science
• Author(s): Wenrui Li* and Eric Kolaczyk and Daniel L Sussman
• Companies: Boston University and Boston University and Boston University
• Keywords: Causal inference ; Noisy network; Interference

Abstract

Increasingly, there is a marked interest in estimating causal effects under network interference due to the fact that interference can manifest itself in networked experiments. Moreover, network information generally is available only up to some level of error. We study the propagation of such errors to estimators of average causal effects under network interference. Specifically, assuming a four-level exposure model and Bernoulli random assignment of treatment, we characterize the impact of network noise on the bias and variance of standard estimators. In addition, we propose new estimators for bias reduction. This is joint work with Eric D. Kolaczyk and Daniel L. Sussman.