Download This Paper Open PDF in Browser

Non-Bayesian Social Learning

25 Pages Posted: 24 Aug 2011 Last revised: 30 Jan 2013

Ali Jadbabaie

Institute for Data, Systems, and Society, Massachusetts Institute of Technology

Pooya Molavi

Massachusetts Institute of Technology (MIT), Department of Economics, Students

Alvaro Sandroni

University of Pennsylvania - Department of Economics; Northwestern University - Kellogg School of Management

Alireza Tahbaz-Salehi

Northwestern University - Kellogg School of Management

Date Written: August 5, 2011

Abstract

We develop a dynamic model of opinion formation in social networks when the information required for learning a payoff-relevant parameter may not be at the disposal of any single agent. Individuals engage in communication with their neighbors in order to learn from their experiences. However, instead of incorporating the views of their neighbors in a fully Bayesian manner, agents use a simple updating rule which linearly combines their personal experience and the views of their neighbors (even though the neighbors’ views may be quite inaccurate). This non-Bayesian learning rule is motivated by the formidable complexity required to fully implement Bayesian updating in networks. We show that, as long as individuals take their personal signals into account in a Bayesian way, repeated interactions lead them to successfully aggregate information and learn the true underlying state of the world. This result holds in spite of the apparent naiveté of agents’ updating rule, the agents’ need for information from sources the existence of which they may not be aware of, the possibility that the most persuasive agents in the network are precisely those least informed and with worst prior views, and the assumption that no agent can tell whether her own views or those of her neighbors are more accurate.

Keywords: Social networks, learning, information aggregation

JEL Classification: D83, L14

Suggested Citation

Jadbabaie, Ali and Molavi, Pooya and Sandroni, Alvaro and Tahbaz-Salehi, Alireza, Non-Bayesian Social Learning (August 5, 2011). PIER Working Paper No. 11-025; Columbia Business School Research Paper No. 13-5. Available at SSRN: https://ssrn.com/abstract=1916109 or http://dx.doi.org/10.2139/ssrn.1916109

Ali Jadbabaie

Institute for Data, Systems, and Society, Massachusetts Institute of Technology ( email )

77 Massachusetts Ave E18-309C
E18-309C
02139, MA MA 02139
United States
6172537339 (Phone)
6172537339 (Fax)

HOME PAGE: http://web.mit.edu/www/jadbabai

Pooya Molavi

Massachusetts Institute of Technology (MIT), Department of Economics, Students ( email )

Cambridge, MA
United States

Alvaro Sandroni (Contact Author)

University of Pennsylvania - Department of Economics ( email )

160 McNeil Building
3718 Locust Walk
Philadelphia, PA 19104
United States

Northwestern University - Kellogg School of Management ( email )

2001 Sheridan Road
Evanston, IL 60208
United States
847-491-5461 (Phone)
847-467-1220 (Fax)

Alireza Tahbaz-Salehi

Northwestern University - Kellogg School of Management ( email )

2001 Sheridan Road
Evanston, IL 60208
United States

Paper statistics

Downloads
278
rank
95,273
Abstract Views
1,307