Spillover Effects in Experimental Data

TL;DR

This paper reviews current methods for estimating treatment and spillover effects in experimental data under interference, emphasizing network and hierarchical structures, and illustrates these with simulations and empirical studies.

Contribution

It provides a comprehensive overview of methods for handling interference in experiments, including network and hierarchical cases, and demonstrates their application using the interference R package.

Findings

Interference affects outcome estimation and must be accounted for in experimental analysis.

Efficient experimental designs enable estimation of both treatment and spillover effects.

Simulations and empirical studies illustrate the practical application of these methods.

Abstract

We present current methods for estimating treatment effects and spillover effects under "interference", a term which covers a broad class of situations in which a unit's outcome depends not only on treatments received by that unit, but also on treatments received by other units. To the extent that units react to each other, interact, or otherwise transmit effects of treatments, valid inference requires that we account for such interference, which is a departure from the traditional assumption that units' outcomes are affected only by their own treatment assignment. Interference and associated spillovers may be a nuisance or they may be of substantive interest to the researcher. In this chapter, we focus on interference in the context of randomized experiments. We review methods for when interference happens in a general network setting. We then consider the special case where interference is contained within a hierarchical structure. Finally, we discuss the relationship between interference and contagion. We use the interference R package and simulated data to illustrate key points. We consider efficient designs that allow for estimation of the treatment and spillover effects and discuss recent empirical studies that try to capture such effects.