An Instrumental Variables Approach to Testing Firm Conduct

2025-01-09

AI Summary

This paper addresses the challenge of detecting collusive behavior among firms in Bertrand oligopolies. We propose a non-nested model testing framework that bypasses joint demand–supply estimation. Our method employs a first-stage price regression with instrumental variables and applies the Rivers–Vuong test to compare the goodness-of-fit of two competing models—collusive versus non-collusive—to directly infer collusion. A key innovation is a BLP-style instrument augmentation strategy: upon detecting collusion, product characteristics of colluding partners are incorporated into the focal firm’s instrument set to enhance identification power. Monte Carlo simulations and robustness checks demonstrate that our approach outperforms or matches existing methods across diverse collusion scenarios—including partial, asymmetric, and multi-firm collusion—and exhibits strong robustness to model misspecification, alternative instrument functional forms, and data limitations. The framework delivers a practical, highly robust empirical paradigm for antitrust enforcement.

Technology Category

• Game Theory and Economic Paradigms: Coordination and Collaboration
• Search and Optimization: Non-convex Optimization
• Multiagent Systems: Mechanism Design

Application Category

• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• Security and Privacy: Large-scale security measurements
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Understanding firm conduct is crucial for industrial organization and antitrust policy. In this article, we develop a testing procedure based on the Rivers and Vuong non-nested model selection framework. Unlike existing methods that require estimating the demand and supply system, our approach compares the model fit of two first-stage price regressions. Through an extensive Monte Carlo study, we demonstrate that our test performs comparably to, or outperforms, existing methods in detecting collusion across various collusive scenarios. The results are robust to model misspecification, alternative functional forms for instruments, and data limitations. By simplifying the diagnosis of firm behavior, our method provides an efficient tool for researchers and regulators to assess industry conduct. Additionally, our approach offers a practical guideline for enhancing the strength of BLP-style instruments in demand estimation: once collusion is detected, researchers are advised to incorporate the product characteristics of colluding partners into own-firm instruments while excluding them from other-firm instruments.

Problem

• Testing firm conduct under Bertrand-Nash framework
• Detecting collusion without estimating demand-supply system
• Enhancing instrument strength in demand estimation post-collusion

Innovation

• Uses first-stage price regressions comparison
• Robust to model misspecification and data limits
• Enhances BLP-style instruments post-collusion detection