Locally Bayesian Learning in Networks

Theoretical Economics, Forthcoming

46 Pages Posted: 4 Dec 2019

See all articles by Wei Li

Wei Li

Vancouver School of Economics, University of British Columbia

Xu Tan

University of Washington - Economics

Date Written: August 27, 2019

Abstract

Agents in a network want to learn the true state of the world from their own signals and their neighbors' reports. Agents know only their local networks, consisting of their neighbors and the links among them. Every agent is Bayesian with the (possibly misspecified) prior belief that her local network is the entire network. We present a tractable learning rule to implement such locally Bayesian learning: each agent extracts new information using the full history of observed reports in her local network. Despite their limited network knowledge, agents learn correctly when the network is a social quilt, a tree-like union of cliques. But they fail to learn when a network contains interlinked circles (echo chambers), despite an arbitrarily large number of correct signals.

Keywords: locally Bayesian learning, rational learning with misspecified priors, efficient learning in finite networks

JEL Classification: D03, D83, D85

Suggested Citation

Li, Wei and Tan, Xu, Locally Bayesian Learning in Networks (August 27, 2019). Theoretical Economics, Forthcoming, Available at SSRN: https://ssrn.com/abstract=3489384

Wei Li (Contact Author)

Vancouver School of Economics, University of British Columbia ( email )

6000 Iona Drive
Vancouver, BC V6T 1L4
Canada
604-822-2839 (Phone)

Xu Tan

University of Washington - Economics ( email )

Seattle, WA
United States

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

Paper statistics

Downloads
14
Abstract Views
140
PlumX Metrics