Network Experiments with Edge Treatments and Node Outcomes

Artem Kuriksha; Kenneth Hung

Home/Archive/arXiv

arXiv · 2610.07363

Network Experiments with Edge Treatments and Node Outcomes

Artem Kuriksha·Kenneth Hung

View original source ↗Read source document ↗Export metadata ↓

Abstract

We present a methodology for analyzing node-level outcomes while experimenting with edge-level treatments in a population connected by an undirected graph. Under our design, nodes are randomly assigned to test or control, and each edge inherits the treatment of its endpoints, with conflicts resolved by randomization. We use each node's assigned status as an instrument for its treatment exposure. We show that the Wald estimator is consistent for the global average treatment effect (GATE), even when the edge weights used to construct the exposure are misspecified. We formalize the assumptions needed both in terms of the linearity of potential outcomes and the sparsity of the graph, and prove the asymptotic normality of the Wald estimator. The estimator is straightforward to implement, requiring no assignment simulations over the graph. Our Monte Carlo study demonstrates the strong performance of our approach in the context of a social platform.

Explore related subjects

econ.EM stat.ME

Keep this discovery

Explore connections, maps & timelines

BibTeX RIS

Artem Kuriksha, Kenneth Hung. 2026-10-05. Network Experiments with Edge Treatments and Node Outcomes. https://arxiv.org/abs/2610.07363

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

Propensity score with factor loadings: evaluating the effect of the Paris Agreement on the returns of European stocks

Factor models for longitudinal data, where policy adoption is unconfounded with respect to a low-dimensional set of latent factor loadings, have become increasingly popular for causal inference. Most existing approaches, however, rely on a causal finite-sample approach or computationally intensive methods, limiting their applicability and external validity. In this paper, we propose a novel method for panel causal inference within a super-population framework, based on inverse propensity score weighting, where the propensity score is a function of latent factor loadings. The approach relaxes the traditional restrictive assumptions of causal panel methods, while offering advantages in terms of causal interpretability, policy relevance, and computational efficiency. Under standard assumptions, we develop a three-step estimation procedure for the ATT and derive its large-sample properties using M-estimation theory. Simulation results show that the proposed estimator remains reliable across a variety of designs, including settings with misspecified factor structure and weakly dependent errors. We apply the method to assess the causal effect of the Paris Agreement - a policy aimed at fostering the transition to a low-carbon economy - on European stock returns. Our empirical results suggest a statistically significant and negative short-run effect on the stock returns of firms that demonstrate a strong commitment to sustainability.

econ.EM↗

arXiv2026

Two Gaussians, Too Many: A bootstrap-based approach to assess identifiability in non-Gaussian structural vector autoregressions

Normality pre-tests on reduced-form innovations cannot detect whether two or more underlying structural shocks are Gaussian, and hence cannot detect a failure of identification in non-Gaussian SVARs. We propose a bootstrap-based approach that reveals such a failure. Under the null of valid identification and certain regularity conditions, the conditional bootstrap distribution of the maximum likelihood estimator of the impact matrix is asymptotically normal, so the diagnostic reduces to a normality test on the bootstrap replications. The impact-matrix estimator remains consistent and asymptotically normal when one shock is Gaussian and its shape parameter lies on the boundary of the parameter space, so the diagnostic is valid across the entire null hypothesis. When the number of bootstrap replications and the sample size diverge jointly at an appropriate rate, the test statistic, conditional on the data, is asymptotically pivotal. This implies that conditioning on this diagnostic does not induce pre-testing bias asymptotically. In simulations with Normal-inverse Gaussian shocks, the multivariate diagnostic is close to its nominal size under the null, its power against an additional Gaussian shock increases with the sample size, and its univariate version localizes the failure in large samples. Based on the estimates of a SVAR in the macroeconomic and financial uncertainty literature, we demonstrate its potential as a practical, robust tool for assessing non-Gaussian identification.

econ.EM↗

arXiv2026

Heterogeneous Policy Effects in Comparative Case Studies with Treated-Unit Microdata

This article develops an identification framework for heterogeneous policy effects when individual-level data are available only in the treated jurisdiction. The framework combines outcome changes from repeated cross-sections within that jurisdiction with a population-average effect identified from aggregate panel data. Under conditional relative parallel trends and overlap, this information identifies subgroup effects standardized to the treated jurisdiction's overall post-treatment covariate distribution, but generally not effects averaged over each subgroup's own distribution. I establish how these subgroup-average effects can nevertheless be recovered using covariate-specific aggregate effects or additional pretreatment observations under assumptions about the evolution of untreated trends. Simulations and an application to the Massachusetts health reform illustrate the framework.

econ.EM↗