Randomized Controlled Trials Under Influence: Covariate Factors and Graph-Based Network Interference

TL;DR

This paper explores how covariate factors and social influence networks affect the design and analysis of randomized controlled trials, proposing new methods for participant assignment and influence modeling to improve trial validity.

Contribution

It introduces a comprehensive graph-based influence model and a novel estimator for treatment effects, addressing covariate balancing and social spillover effects in RCTs.

Findings

A review of a covariate-aware assignment algorithm with good variance bounds

Development of a new average treatment effect estimator considering social influence

Analysis of the impact of network structure on trial outcomes

Abstract

Randomized controlled trials are not only the golden standard in medicine and vaccine trials but have spread to many other disciplines like behavioral economics, making it an important interdisciplinary tool for scientists. When designing randomized controlled trials, how to assign participants to treatments becomes a key issue. In particular in the presence of covariate factors, the assignment can significantly influence statistical properties and thereby the quality of the trial. Another key issue is the widely popular assumption among experimenters that participants do not influence each other -- which is far from reality in a field study and can, if unaccounted for, deteriorate the quality of the trial. We address both issues in our work. After introducing randomized controlled trials bridging terms from different disciplines, we first address the issue of participant-treatment assignment in the presence of known covariate factors. Thereby, we review a recent assignment algorithm that achieves good worst-case variance bounds. Second, we address social spillover effects. Therefore, we build a comprehensive graph-based model of influence between participants, for which we design our own average treatment effect estimator $\hat \tau_{net}$. We discuss its bias and variance and reduce the problem of variance minimization to a certain instance of minimizing the norm of a matrix-vector product, which has been considered in literature before. Further, we discuss the role of disconnected components in the model's underlying graph.