Regression with Observational Multilayered Network Data

📅 2026-08-02
📈 Citations: 0
Influential: 0
📄 PDF
🤖 AI Summary
This study addresses the bias in estimating social effects from non-experimental, multidimensional network data due to endogeneity, measurement error, and unobserved heterogeneity in linear mean regression models. To tackle these challenges, the paper proposes a closed-form generalized three-stage least squares (G3SLS) estimator that leverages a two-layer multiplex network structure. By exploiting exogenous network layers to identify endogenous social interactions, this approach introduces multiplex network structures into social effect identification for the first time, yielding an estimator that is consistent, asymptotically normal, and computationally tractable. Monte Carlo simulations demonstrate the superior finite-sample performance of G3SLS, while empirical analysis reveals a significant positive peer effect in citation behavior among top economics journals.
📝 Abstract
A novel method to estimate social effect coefficients in the popular so-called linear-in-means regression model in the Social Sciences is presented here that utilizes non-experimental multidimensional network data. The procedure can accommodate social interactions that correlate with the error in the model by making use of a different set of network links among the same observations that are exogenous in the traditional sense. In particular, the full observability of a two-layered multiplex network data structure is assumed here to propose a new Generalized 3-Stage Least Squares (G3SLS) estimator that is consistent, asymptotically normally distributed, and also easy to implement using widely-used existing statistical software because of its closed-form definition. The underlying assumptions are general enough to accommodate common problems with observational data such as measurement error, simultaneity, and unobserved heterogeneity. Monte Carlo exercises confirm the good small sample performance of the proposed G3SLS estimator in these scenarios. An empirical application finds positive and significant peer effects in citations among research articles published in top general-interest journals in economics.
Problem

Research questions and friction points this paper is trying to address.

social effects
observational network data
endogeneity
peer effects
multilayered networks
Innovation

Methods, ideas, or system contributions that make the work stand out.

multilayered network
peer effects
G3SLS estimator
linear-in-means model
observational data
🔎 Similar Papers
J
Juan Estrada
Analysis Group Economic Consulting, Washington, DC, USA
K
Kim Huynh
Department of Economics, Indiana University, 100 S Woodlawn, Bloomington, IN 47405, USA. The Laboratoire d’Économie d’Orléans, Université d’Orléans, Orléans, France
D
David Jacho-Chavez
Department of Economics, Emory University, Rich Building 306, 1602 Fishburne Dr., Atlanta, GA 30322-2240, USA
L
Leonardo Sanchez-Aragon
Facultad de Ciencias Sociales y Humanísticas, Escuela Superior Politécnica del Litoral, ESPOL, Campus Gustavo Galindo Km. 30.5 Vía Perimetral, P.O. Box 09-01-5863, Guayaquil, Ecuador