Estimating average causal effects under general interference, with application to a social network experiment

@article{Aronow2017EstimatingAC,
  title={Estimating average causal effects under general interference, with application to a social network experiment},
  author={Peter M. Aronow and Cyrus Samii},
  journal={The Annals of Applied Statistics},
  year={2017},
  volume={11},
  pages={1912-1947}
}
This paper presents a randomization-based framework for estimating causal effects under interference between units, motivated by challenges that arise in analyzing experiments on social networks. The framework integrates three components: (i) an experimental design that defines the probability distribution of treatment assignments, (ii) a mapping that relates experimental treatment assignments to exposures received by units in the experiment, and (iii) estimands that make use of the experiment… 

Figures and Tables from this paper

Causal Inference Under Approximate Neighborhood Interference
TLDR
It is proved that standard inverse‐probability weighting estimators consistently estimate useful exposure effects and are approximately normal, and Neyman's well‐known result on conservative variance estimation to settings with interference is generalized.
Elements of estimation theory for causal effects in the presence of network interference
Randomized experiments in which the treatment of a unit can affect the outcomes of other units are becoming increasingly common in healthcare, economics, and in the social and information sciences.
Causal Inference under Networked Interference
TLDR
This work studies causal effect estimation under general network interference using GNNs, which are powerful tools for capturing the dependency in the graph and gives policy regret bounds under network interference and treatment capacity constraint.
Random Graph Asymptotics for Treatment Effect Estimation under Network Interference
The network interference model for causal inference places all experimental units at the vertices of an undirected exposure graph, such that treatment assigned to one unit may affect the outcome of
Randomized experiments to detect and estimate social influence in networks
TLDR
This review discusses the design space of experiments to measure social influence through combinations of interventions and randomizations and shows how randomization also provides a basis for statistical inference when analyzing these experiments.
Identification and Estimation of Treatment and Interference Effects in Observational Studies on Networks
TLDR
An extended unconfoundedness assumption that accounts for interference is proposed, and new covariate-adjustment methods are developed that lead to valid estimates of treatment and interference effects in observational studies on networks.
Graph Agnostic Randomized Experimental Design under Heterogeneous Linear Network Interference
TLDR
This work considers a heterogeneous linear outcomes model that can capture network interference that arises from spillover, peer effects, and contagion and proposes simple estimators and randomized designs that output unbiased estimates with low variance for these three estimands.
Causal Network Motifs: Identifying Heterogeneous Spillover Effects in A/B Tests
TLDR
This study provides an approach that accounts for both the local structure in a user’s social network via motifs as well as the treatment assignment conditions of neighbors, and proposes a tree-based algorithm for identifying different network interference conditions and estimating their average potential outcomes.
Causal Inference under Networked Interference and Intervention Policy Enhancement
TLDR
This work study causal effect estimation under general network interference using Graph Neural Networks, which are powerful tools for capturing node and link dependencies in graphs, and deriving causal effect estimators.
Causal Inference With Interference and Noncompliance in Two-Stage Randomized Experiments
Abstract In many social science experiments, subjects often interact with each other and as a result one unit’s treatment influences the outcome of another unit. Over the last decade, a significant
...
...

References

SHOWING 1-10 OF 67 REFERENCES
Design and Analysis of Experiments in Networks: Reducing Bias from Interference
TLDR
This work evaluates methods for designing and analyzing randomized experiments under minimal, realistic assumptions compatible with broad interference, finding substantial bias reductions and, despite a bias–variance tradeoff, error reductions.
Graph cluster randomization: network exposure to multiple universes
TLDR
It is shown that proper cluster randomization can lead to exponentially lower estimator variance when experimentally measuring average treatment effects under interference, and if a graph satisfies a restricted-growth condition on the growth rate of neighborhoods, then there exists a natural clustering algorithm, based on vertex neighborhoods, for which the variance of the estimator can be upper bounded by a linear function of the degrees.
Estimation of Causal Peer Influence Effects
TLDR
This paper extends potential outcomes to allow for interference, well-defined causal estimands of peer-inuence are introduced, and two estimation procedures are developed: a frequentist procedure relying on a sequential randomization design that requires knowledge of the network but operates under complicated response functions, and a Bayesian procedure which accounts for network uncertainty but relies on a linear response assumption to increase estimation precision.
Large Sample Randomization Inference of Causal Effects in the Presence of Interference
TLDR
This article considers inference about effects when the population consists of groups of individuals where interference is possible within groups but not between groups, and considers the effects of cholera vaccination and an intervention to encourage voting.
Toward Causal Inference With Interference
TLDR
This article considers a population of groups of individuals where interference is possible between individuals within the same group, and proposes estimands for direct, indirect, total, and overall causal effects of treatment strategies in this setting.
Reasoning about Interference Between Units: A General Framework
TLDR
This article shows how counterfactual causal models may be written and tested when theories suggest spillover or other network-based interference among experimental units, and offers researchers the ability to model theories about how treatment given to some units may come to influence outcomes for other units.
What Do Randomized Studies of Housing Mobility Demonstrate?
TLDR
A frame-work for causal inference when interference is present is developed and a number of causal estimands of interest are defined, which are of great importance for a researcher who fails to recognize that a treatment is beneficial when in fact it is universally harmful.
Causal Inference for Statistics, Social, and Biomedical Sciences: An Introduction
Most questions in social and biomedical sciences are causal in nature: what would happen to individuals, or to groups, if part of their environment were changed? In this groundbreaking text, two
On causal inference in the presence of interference
TLDR
This article summarises some of the concepts and results from the existing literature and extends that literature in considering new results for finite sample inference, new inverse probability weighting estimators in the presence of interference and new causal estimands of interest.
...
...