Network Regression and Supervised Centrality Estimation

76 Pages Posted: 28 Nov 2021

See all articles by Junhui Cai

Junhui Cai

University of Notre Dame - Mendoza College of Business

Dan Yang

The University of Hong Kong

Wu Zhu

School of Economics and Management, Tsinghua University

Haipeng Shen

The University of Hong Kong - Faculty of Business and Economics

Linda Zhao

University of Pennsylvania - Statistics Department

Date Written: November 15, 2021

Abstract

The centrality in a network is a popular metric for agents' network positions and is often used in regression models to model the network effect on an outcome variable of interest. In empirical studies, researchers often adopt a two-stage procedure to first estimate the centrality and then infer the network effect using the estimated centrality. Despite its prevalent adoption, this two-stage procedure lacks theoretical backing and can fail in both estimation and inference. We, therefore, propose a unified framework, under which we prove the shortcomings of the two-stage in centrality estimation and the undesirable consequences in the regression. We then propose a novel supervised network centrality estimation (SuperCENT) methodology that simultaneously yields superior estimations of the centrality and the network effect and provides valid and narrower confidence intervals than those from the two-stage. We showcase the superiority of SuperCENT in predicting the currency risk premium based on the global trade network.

Keywords: Hub and authority centrality, Network regression inference, Measurement error, Hyperlink Induced Topic Search (HITS) Algorithm, Global trade network, Currency risk premium

JEL Classification: D85, C10, C18, C30, G15, F10

Suggested Citation

Cai, Junhui and Yang, Dan and Zhu, Wu and Shen, Haipeng and Zhao, Linda, Network Regression and Supervised Centrality Estimation (November 15, 2021). Available at SSRN: https://ssrn.com/abstract=3963523 or http://dx.doi.org/10.2139/ssrn.3963523

Junhui Cai

University of Notre Dame - Mendoza College of Business

Mendoza college of business
University of Notre Dame
Notre Dame, IN 46556-5646
United States

Dan Yang

The University of Hong Kong ( email )

Pokfulam Road
Hong Kong
China

Wu Zhu (Contact Author)

School of Economics and Management, Tsinghua University ( email )

Beijing, PA 19104
China

Haipeng Shen

The University of Hong Kong - Faculty of Business and Economics ( email )

Hong Kong

Linda Zhao

University of Pennsylvania - Statistics Department ( email )

Wharton School
Philadelphia, PA 19104
United States

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
71
Abstract Views
381
Rank
516,682
PlumX Metrics