Causal Inference with Networked Treatment Diffusion

Abstract

Treatment interference (i.e., one unit’s potential outcomes depend on other units’ treatment) is prevalent in social settings. Ignoring treatment interference can lead to biased estimates of treatment effects and incorrect statistical inferences. Some recent studies have started to incorporate treatment interference into causal inference. But treatment interference is often assumed to follow a simple structure (e.g., treatment interference exists only within groups) or measured in a simplistic way (e.g., only based on the number of treated friends). In this paper, I highlight the importance of collecting data on actual treatment diffusion in order to more accurately measure treatment interference. Furthermore, I show that with accurate measures of treatment interference, we can identify and estimate a series of causal effects that are previously unavailable, including the direct treatment effect, treatment interference effect, and treatment effect on interference. I illustrate the methods through a case study of a social network–based smoking prevention intervention.

Opening the Blackbox of Treatment Interference: Tracing Treatment Diffusion through Network Analysis

“…Overall, we conclude that studying treatment diffusion is very important, not only for the sake of propagating treatment diffusion in health and social interventions but also for the purpose of imputing treatment diffusion data, which is crucial for making valid causal inference under treatment interference (An 2018). In addition, it should be pointed out that treatment diffusion can serve not only as a concrete form of treatment interference but also as a mechanism for outcome interference, namely, correlation in outcomes of socially connected units (An 2011, 2015a; VanderWeele and An 2013; VanderWeele, Tchetgen, and Halloran 2012).…”

“…However, we suspect the main patterns of treatment diffusion found in this study like the network processes and the estimates on some covariates are going to hold quite generally. Once the treatment diffusion data are imputed, as shown in An (2018), one can use the data to construct treatment interference measures (e.g., based on the centrality measures in the treatment diffusion networks) and use them in regressions or matching to estimate a series of distinctive causal effects that are unavailable previously, including the direct treatment effect on a substantive outcome, the treatment interference effect on the substantive outcome, and the treatment effect on interference.…”

“…Second, the findings will be useful for imputing treatment diffusion data. Some prior work (An 2018) has developed methods to draw causal inferences in the presence of treatment diffusion. However, treatment diffusion data are not always available.…”

Bipartite Interference and Air Pollution Transport: Estimating Health Effects of Power Plant Interventions

“…The most typical examples include vaccine interventions with effects propagating across infection networks of individuals who come into contact with one another and informational interventions on individuals connected through their social network. Methods for causal inference with interference have motivated much recent work (Hudgens and Halloran, 2008;Bowers et al, 2013;Liu and Hudgens, 2014;Aronow and Samii, 2017;Karwa and Airoldi, 2018;Tchetgen and VanderWeele, 2012;Liu and Hudgens, 2014;Liu et al, 2016;Forastiere et al, 2018Forastiere et al, , 2020Sävje et al, 2017;An, 2018;Papadogeorgou et al, 2019;An and VanderWeele, 2019).…”

“…Unlike the common setting where interference arises due to unit-to-unit outcome dependencies (e.g., one person's vaccination status impacts another person's infection risk), interference in this case arises due to complex exposure patterns governed by the movement of air pollution from an originating source (a power plant) across long distances towards impact on populations. Interference due to complex exposure patterns (or treatment diffusion) has been considered in the causal inference literature, albeit with less frequency than settings of interference due to unit-to-unit outcome dependencies and only emerging focus on explicitly spatial data (Verbitsky-Savitz and Raudenbush, 2012;Graham et al, 2013;An, 2018;An and VanderWeele, 2019;Giffin et al, 2020). To characterize the structure of interference, we deploy a newly-developed reduced-complexity atmospheric model, called HYSPLIT Average Dispersion (HyADS), to model the movement of pollution through space and time (Henneman et al, 2019a).…”