Foundations of Non-Bayesian Social Learning

41 Pages Posted: 31 Oct 2015 Last revised: 16 Nov 2019

See all articles by Pooya Molavi

Pooya Molavi

Northwestern University

Alireza Tahbaz-Salehi

Northwestern University - Kellogg School of Management; Centre for Economic Policy Research (CEPR)

Ali Jadbabaie

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

Date Written: August 2017

Abstract

This paper studies the behavioral foundations of non-Bayesian models of learning over social networks and develops a taxonomy of conditions for information aggregation in a general framework. As our main behavioral assumption, we postulate that agents follow social learning rules that satisfy "imperfect recall", according to which they treat the current beliefs of their neighbors as sufficient statistics for the entire history of their observations. We augment this assumption with various restrictions on how agents process the information provided by their neighbors and obtain representation theorems for the corresponding learning rules (including the canonical model of DeGroot). We then obtain general long-run learning results that are not tied to the learning rules' specific functional forms, thus identifying the fundamental forces that lead to learning, non-learning, and mislearning in social networks. Our results illustrate that, in the presence of imperfect recall, long-run aggregation of information is closely linked to (i) the rate at which agents discount their neighbors' information over time, (ii) the curvature of agents' social learning rules, and (iii) whether their initial tendencies are amplified or moderated as a result of social interactions.

Keywords: social networks, non-Bayesian learning, imperfect recall

JEL Classification: D83, D85

Suggested Citation

Molavi, Pooya and Tahbaz-Salehi, Alireza and Jadbabaie, Ali, Foundations of Non-Bayesian Social Learning (August 2017). Columbia Business School Research Paper No. 15-95, Available at SSRN: https://ssrn.com/abstract=2683607 or http://dx.doi.org/10.2139/ssrn.2683607

Pooya Molavi

Northwestern University ( email )

2001 Sheridan Road
Evanston, IL 60208
United States

Alireza Tahbaz-Salehi (Contact Author)

Northwestern University - Kellogg School of Management ( email )

2001 Sheridan Road
Evanston, IL 60208
United States

Centre for Economic Policy Research (CEPR) ( email )

London
United Kingdom

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

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

Paper statistics

Downloads
358
Abstract Views
1,664
rank
109,156
PlumX Metrics