Designs for estimating the treatment effect in networks with interference
From MaRDI portal
Publication:2196188
Abstract: In this paper we introduce new, easily implementable designs for drawing causal inference from randomized experiments on networks with interference. Inspired by the idea of matching in observational studies, we introduce the notion of considering a treatment assignment as a quasi-coloring" on a graph. Our idea of a perfect quasi-coloring strives to match every treated unit on a given network with a distinct control unit that has identical number of treated and control neighbors. For a wide range of interference functions encountered in applications, we show both by theory and simulations that the classical Neymanian estimator for the direct effect has desirable properties for our designs. This further extends to settings where homophily is present in addition to interference.
Recommendations
- Identification and estimation of treatment and interference effects in observational studies on networks
- Random graph asymptotics for treatment effect estimation under network interference
- Efficient semiparametric estimation of network treatment effects under partial interference
- Model-assisted design of experiments in the presence of network-correlated outcomes
- A critical threshold for design effects in network sampling
- Estimating average causal effects under general interference, with application to a social network experiment
- A Graph-Theoretic Approach to Randomization Tests of Causal Effects under General Interference
- Estimation and inference on treatment effects under treatment-based sampling designs
- Inferring network structure from interventional time-course experiments
Cites work
- Bayesian inference for causal effects: The role of randomization
- Collective dynamics of `small-world' networks
- Emergence of Scaling in Random Networks
- Estimating average causal effects under general interference, with application to a social network experiment
- For objective causal inference, design trumps analysis
- Latent Space Approaches to Social Network Analysis
- Model-assisted design of experiments in the presence of network-correlated outcomes
- Spectra of edge-independent random graphs
- Statistics and Causal Inference
- Toward Causal Inference With Interference
Cited in
(14)- Identification and estimation of treatment and interference effects in observational studies on networks
- Testing for arbitrary interference on experimentation platforms
- Efficient semiparametric estimation of network treatment effects under partial interference
- Estimating average causal effects under general interference, with application to a social network experiment
- Cluster allocation design networks
- Exact \(p\)-values for network interference
- Community informed experimental design
- Auto-g-computation of causal effects on a network
- Causal inference under approximate neighborhood interference
- Design of randomized experiments to measure social interaction effects
- Rate-optimal cluster-randomized designs for spatial interference
- Average treatment effects in the presence of unknown interference
- Model-assisted design of experiments in the presence of network-correlated outcomes
- Network and covariate adjusted response-adaptive design for binary response
This page was built for publication: Designs for estimating the treatment effect in networks with interference
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2196188)
