Inferring Latent Social Networks from Stock Holdings

58 Pages Posted: 22 Jul 2015 Last revised: 13 Sep 2017

See all articles by Harrison G. Hong

Harrison G. Hong

Columbia University, Graduate School of Arts and Sciences, Department of Economics; National Bureau of Economic Research (NBER)

Jiangmin Xu

Peking University - Department of Finance

Multiple version iconThere are 2 versions of this paper

Date Written: September 11, 2017

Abstract

We infer the latent social networks of investors using data on their stock holdings. We map linkages to portfolio weights using a portfolio-choice model. The precision of an investor's private signal about firm value is assumed to increase with his connections in the city where the firm is headquartered. Using money-manager data, we find that managerial linkages to a city are overly dispersed relative to the Erdös-Rényi model of i.i.d. connections. Managers at the tail of this distribution with non-i.i.d. linkages have more university alumni in that city. Their stock holdings there outperform their holdings in other cities.

Keywords: Social Networks, Poisson Regressions, Investor Behavior

JEL Classification: G1, G2, G3

Suggested Citation

Hong, Harrison G. and Xu, Jiangmin, Inferring Latent Social Networks from Stock Holdings (September 11, 2017). Journal of Financial Economics (JFE), Forthcoming. Available at SSRN: https://ssrn.com/abstract=2634306 or http://dx.doi.org/10.2139/ssrn.2634306

Harrison G. Hong

Columbia University, Graduate School of Arts and Sciences, Department of Economics ( email )

420 W. 118th Street
New York, NY 10027
United States

National Bureau of Economic Research (NBER)

1050 Massachusetts Avenue
Cambridge, MA 02138
United States

Jiangmin Xu (Contact Author)

Peking University - Department of Finance ( email )

5 Yiheyuan Road
Beijing 100871
China

Here is the Coronavirus
related research on SSRN

Paper statistics

Downloads
590
Abstract Views
2,916
rank
25,304
PlumX Metrics