Estimation of Monotone Treatment Effects in Network Experiments

TL;DR

This paper introduces new methods for estimating treatment effects in social network experiments, addressing interference issues without needing partial interference assumptions, and leveraging network data to improve statistical power.

Contribution

It proposes novel estimation techniques for network experiments that do not rely on partial interference, utilizing network information to enhance test power.

Findings

Methods effectively estimate attributable effects in network settings.

Network data customization can increase statistical power.

Approach does not require strong assumptions like partial interference.

Abstract

Randomized experiments on social networks pose statistical challenges, due to the possibility of interference between units. We propose new methods for estimating attributable treatment effects in such settings. The methods do not require partial interference, but instead require an identifying assumption that is similar to requiring nonnegative treatment effects. Network or spatial information can be used to customize the test statistic; in principle, this can increase power without making assumptions on the data generating process.