Average treatment effects in the presence of unknown interference
From MaRDI portal
Publication:2039779
Abstract: We investigate large-sample properties of treatment effect estimators under unknown interference in randomized experiments. The inferential target is a generalization of the average treatment effect estimand that marginalizes over potential spillover effects. We show that estimators commonly used to estimate treatment effects under no interference are consistent for the generalized estimand for several common experimental designs under limited but otherwise arbitrary and unknown interference. The rates of convergence depend on the rate at which the amount of interference grows and the degree to which it aligns with dependencies in treatment assignment. Importantly for practitioners, the results imply that if one erroneously assumes that units do not interfere in a setting with limited, or even moderate, interference, standard estimators are nevertheless likely to be close to an average treatment effect if the sample is sufficiently large. Conventional confidence statements may, however, not be accurate.
It is noted that causal inference usually assumes the absence of interference among the units of the population. However, in certain situations ,especially in social and medical fields, interference is inevitable. In such cases, it is possible to allow moderate amounts of interference in an unknown and arbitrary way. A sample of units is selected and a random subset is assigned to a particular treatment. Here the parameter of interest is the average effect of the assignments under spill over effects. The authors investigate the expected average treatment effect (EATE). They obtain consistent estimates of EATE as well as their variance estimates using Horvitz-Thompson and Ha'jek estimators. Furthermore, they show that EATE for a given experiment is informative of the effect under the designs that are close to the implemented design. Thus external validity is established with a proper definition of measure of closeness, which is an important practical aspect. There is a simulation study in one of the three supplements provided at the end of the paper.
Recommendations
- Interference Between Units in Randomized Experiments
- Estimating average causal effects under general interference, with application to a social network experiment
- Causal inference under approximate neighborhood interference
- Large sample randomization inference of causal effects in the presence of interference
- Toward Causal Inference With Interference
Cites work
- A CENTRAL LIMIT THEOREM AND A STRONG MIXING CONDITION
- A Generalization of Sampling Without Replacement From a Finite Universe
- Agnostic notes on regression adjustments to experimental data: reexamining Freedman's critique
- Analyzing two-stage experiments in the presence of interference
- Confidence intervals for linear unbiased estimators under constrained dependence
- Designs for estimating the treatment effect in networks with interference
- Effect partitioning under interference in two-stage randomized vaccine trials
- Efficient Estimation of Average Treatment Effects Using the Estimated Propensity Score
- Estimating average causal effects under general interference, with application to a social network experiment
- Exact \(p\)-values for network interference
- Exact confidence intervals in the presence of interference
- scientific article; zbMATH DE number 3137858 (Why is no real title available?)
- Identification and estimation of econometric models with group interactions, contextual factors and fixed effects
- Identification and Estimation of Local Average Treatment Effects
- Identification of Endogenous Social Effects: The Reflection Problem
- Identification of peer effects through social networks
- Identification of treatment response with social interactions
- Identifying Social Interactions Through Conditional Variance Restrictions
- Inference with interference between units in an fMRI experiment of motor inhibition
- Interference Between Units in Randomized Experiments
- Large sample randomization inference of causal effects in the presence of interference
- Model-assisted design of experiments in the presence of network-correlated outcomes
- Normal approximation under local dependence.
- On inverse probability-weighted estimators in the presence of interference
- On mitigating the analytical limitations of finely stratified experiments
- On the application of probability theory to agricultural experiments. Essay on principles. Section 9. Translated from the Polish and edited by D. M. Dąbrowska and T. P. Speed
- On the Convergence of the Horvitz-Thompson Estimator
- On the Kantorovich-Rubinstein theorem
- On the Role of the Propensity Score in Efficient Semiparametric Estimation of Average Treatment Effects
- On the strong law of large numbers for a class of stochastic processes
- Randomization tests of causal effects under interference
- Statistics and Causal Inference
- Survey Design Under the Regression Superpopulation Model
- Toward Causal Inference With Interference
- Vaccines, contagion, and social networks
- What Do Randomized Studies of Housing Mobility Demonstrate?
Cited in
(38)- Estimating average causal effects under general interference, with application to a social network experiment
- Randomization for the susceptibility effect of an infectious disease intervention
- Random graph asymptotics for treatment effect estimation under network interference
- Rate-optimal cluster-randomized designs for spatial interference
- Who should get vaccinated? Individualized allocation of vaccines over SIR network
- Assessing the causal effects of financial aids to firms in Tuscany allowing for interference
- Design and analysis of bipartite experiments under a linear exposure-response model
- What Do Randomized Studies of Housing Mobility Demonstrate?
- Inference with interference between units in an fMRI experiment of motor inhibition
- Testing for arbitrary interference on experimentation platforms
- Interference Between Units in Randomized Experiments
- On inverse probability-weighted estimators in the presence of interference
- Average direct and indirect causal effects under interference
- Design of agricultural field experiments accounting for both complex blocking structures and network effects
- Community informed experimental design
- Instrumental variable analysis for cost outcome: Application to the effect of primary care visit on medical cost among low‐income adults
- Estimating a Continuous Treatment Model with Spillovers: A Control Function Approach
- Evaluating Dynamic Conditional Quantile Treatment Effects with Applications in Ridesharing
- New Estimands for Experiments with Strong Interference
- Causal Inference with Noncompliance and Unknown Interference
- The local approach to causal inference under network interference
- Causal effect estimation under network interference with mean-field methods
- Degree of interference: a general framework for causal inference under interference
- Model-twin randomization (MoTR) for estimating the recurring individual treatment effect
- Causal inference in network experiments: regression-based analysis and design-based properties
- A continuous-time stochastic process for high-resolution network data in sports
- Policy targeting under network interference
- Design-based inference for spatial experiments under unknown interference
- A Bayesian analysis of two-stage randomized experiments in the presence of interference, treatment nonadherence, and missing outcomes
- Optimal transport and Wasserstein distances for causal models
- Causal inference over stochastic networks
- Bayesian empirical likelihood regression for semiparametric estimation of optimal dynamic treatment regimes
- Causal inference with misspecified network interference structure
- A review of causal decision making
- Difference-in-differences with interference
- A design-based approach to spatial correlation
- Exact confidence intervals in the presence of interference
- Statistical Inference and Power Analysis for Direct and Spillover Effects in Two-Stage Randomized Experiments
This page was built for publication: Average treatment effects in the presence of unknown interference
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2039779)
