Network Effects in Corporate Emissions: Evidence from a Data-Dependent Spatial Panel Model

2026-02-24

AI Summary

This study investigates the spillover effects of corporate toxic emissions and their network transmission mechanisms. Leveraging a panel dataset of U.S. industrial facilities from 2000 to 2023, the paper eschews pre-specified network structures and instead endogenously identifies emission impact networks through high-dimensional data, constructing a data-driven spatial panel model to flexibly estimate both direct and indirect facility-level effects. The findings reveal that approximately 28% of the total emission effect stems from indirect spillovers—substantially higher than estimates derived from conventional network specifications based on geographic proximity or industry classification—thereby exposing systematic biases in those traditional approaches. This methodology offers a more reliable network foundation for environmental risk assessment and targeted regulatory interventions.

Technology Category

• Data Mining & Knowledge Management: Mining of Spatial, Temporal or Spatio-Temporal Data
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Reasoning under Uncertainty: Relational Probabilistic Models

Application Category

• Social Networks and Social Media: Social media analysis through the lenses of networks
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems

Abstract

We study spillover effects in corporate toxic emissions using a heterogeneous panel network of U.S. industrial facilities from 2000-2023. Rather than imposing a network structure a priori, we uncover an unobserved web of influence directly from the data using recent advances in high-dimensional network econometrics. Indirect effects transmitted through the estimated network account for about 28% of the total impact of key firm balance-sheet characteristics. By contrast, distance-based networks generate no statistically discernible spillovers, while a priori firm- or industry-based networks substantially overstate within-group spillins relative to the data-driven network. These findings show that who is linked to whom, and with what strength, matters critically for assessing systemic environmental risk and for designing targeted regulation. Methodologically, the paper provides a flexible framework for quantifying facility-level emissions spillovers and their consequences in financial and policy settings.

Problem

• network effects
• corporate emissions
• spillover effects
• environmental risk
• spatial panel model

Innovation

• data-driven network
• spatial panel model
• emissions spillovers
• high-dimensional network econometrics
• systemic environmental risk