A partial identification subnetweork approach to discrete games in large networks; Application to quantifying peer effects

Citation

Li, Tong & Zhao, Li (2017). A partial identification subnetweork approach to discrete games in large networks; Application to quantifying peer effects. Seattle-Vancouver Econometrics Conference. Seattle, US.

Abstract

This paper studies identification and estimation of discrete games in large networks, with an application to peer e§ects on smoking in friend networks. Due to the presence of multiple equilibria, the model is not point identified. We adopt the partial identification approach by constructing moment inequalities on choice probabilities of subnetworks. Doing so not only significantly reduces the computational cost, but also enables us to find consistent estimator of the moment conditions even when the network is large and the friendship relationship structure varies significantly among networks. Monte Carlo studies are conducted to evaluate the performance of the subnetwork approach. In the application using the Add Health data, we find signficant and positive peer e§ects on smoking.

URL

https://pdfs.semanticscholar.org/1bdd/4e9f6cae9d1babbde2c1a307dc148f4d8765.pdf

Reference Type

Conference proceeding

Book Title

Seattle-Vancouver Econometrics Conference

Author(s)

Li, Tong
Zhao, Li

Year Published

2017

City of Publication

Seattle, US

Reference ID

9226