TY - JOUR
T1 - Non-Bayesian social learning
AU - Jadbabaie, Ali
AU - Molavi, Pooya
AU - Sandroni, Alvaro
AU - Tahbaz-Salehi, Alireza
N1 - Funding Information:
✩ We thank the editors, Vincent Crawford and Matthew Jackson, and two anonymous referees for very helpful remarks and suggestions. We also thank Ilan Lobel and numerous seminar and conference participants for useful feedback and comments. Jadbabaie, Molavi and Tahbaz-Salehi gratefully acknowledge financial support from the Air Force Office of Scientific Research (Complex Networks Program) and the Office of Naval Research. Sandroni gratefully acknowledges the financial support of the National Science Foundation (Grants SES-0820472 and SES-0922404). * Corresponding author. E-mail address: sandroni@kellogg.northwestern.edu (A. Sandroni).
PY - 2012/9
Y1 - 2012/9
N2 - We develop a dynamic model of opinion formation in social networks when the information required for learning a 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. 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 parameter. This result holds in spite of the apparent naïveté of agents' updating rule, the agents' need for information from sources the existence of which they may not be aware of, worst prior views, and the assumption that no agent can tell whether her own views or those of her neighbors are more accurate.
AB - We develop a dynamic model of opinion formation in social networks when the information required for learning a 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. 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 parameter. This result holds in spite of the apparent naïveté of agents' updating rule, the agents' need for information from sources the existence of which they may not be aware of, worst prior views, and the assumption that no agent can tell whether her own views or those of her neighbors are more accurate.
KW - Information aggregation
KW - Learning
KW - Social networks
UR - http://www.scopus.com/inward/record.url?scp=84864323717&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84864323717&partnerID=8YFLogxK
U2 - 10.1016/j.geb.2012.06.001
DO - 10.1016/j.geb.2012.06.001
M3 - Article
AN - SCOPUS:84864323717
SN - 0899-8256
VL - 76
SP - 210
EP - 225
JO - Games and Economic Behavior
JF - Games and Economic Behavior
IS - 1
ER -