SMU SOE Seminar (Mar 15, 2019): Normal Approximation in Large Network Models

Please click here if you are unable to view this page.

ABSTRACT We prove central limit theorems under large-network asymptotics for empirical models of network formation and network processes with homophilous agents. These results enable inference in a large class of network models in the typical setting where the sample consists of a small set of large networks. We first establish a central limit theorem under high-level ``stabilization'' conditions that provide a general and useful formulation of weak dependence, particularly in models with strategic interactions. The result delivers a $\sqrt{n}$ rate of convergence and a closed-form expression for the asymptotic variance. Using techniques in branching process theory, we derive primitive conditions for stabilization in the following applications: static and dynamic models of strategic network formation, network regressions, and treatment effects with network spillovers. Finally, we discuss practical methods for inference, including a HAC-type variance estimator. Click here to view the CV.
		PRESENTER Michael Leung University of Southern California
		RESEARCH FIELDS Econometrics Networks
		DATE: 15 March 2019 (Friday)
		TIME: 4pm - 5.30pm
		VENUE: Meeting Room 5.1, Level 5 School of Economics Singapore Management University 90 Stamford Road Singapore 178903