Estimating social influence in a social network using potential outcomes.

Abstract

Social influence occurs when an individual's outcome is affected by another individual's actions. Current approaches in psychology that seek to examine social influence have focused on settings where individuals are nested in pre-defined groups and do not interact across groups. Such study designs permit using standard estimation methods such as multilevel models for estimating treatment effects, but restrict social influence to originate only from individuals within the same group. In more general settings such as social networks where an individual is free to interact with any other individual, the absence of discernible clusters or scientifically meaningful groups precludes existing estimation methods. In this article, we introduce a new class of methods for assessing social influence in social networks in the context of randomized experiments in psychology. Our proposal builds on the potential outcomes framework from the causal inference literature. In particular, we exploit the concept of (treatment) interference, which occurs between individuals when one individual's outcome is affected by other individuals' treatments. Estimation proceeds using randomization-based approaches that are established in other disciplines and guarantee valid inference by construction. We compared the proposed methods with standard methods empirically using Monte Carlo simulation studies. We illustrated the method using publicly available data from an experiment assessing the effects of an anti-conflict intervention among students' peer networks. The R scripts used to implement the proposed methods in the simulation studies and the applied example are freely available online.

The Causal Cookbook: Recipes for Propensity Scores, G-Computation, and Doubly Robust Standardization

“…For example, noninterference may be violated if our study includes several people living together: In such a scenario, an attendee may counsel a nonattendee, thus leading to a “spillover” of the action. Although such spillover is a nuisance when estimating action effects, it may be of interest in its own right because it leads to other (causal) research questions (Loh & Ren, 2022). Consistency and noninterference are often jointly summarized as the stable unit treatment value assumption (Rubin, 1974).…”

Complexity in Epidemiology and Public Health. Addressing Complex Health Problems Through a Mix of Epidemiologic Methods and Data

“…Others have tried to capture social interference and network clustering of diseases or risk factors in multi-level analyses in families, schools, or workplaces. 53 Apart from these influential lines of work, and a growing body of technical work in this area, [54][55][56][57][58][59] most empirical epidemiologic studies are still based on an unrealistic assumption of no interference between individuals in social networks, probably because highly granular network data is not available. This constitutes a knowledge gap in epidemiology and calls for investment in data collection that will match the technical developments.…”