Non-Bayesian Social Learning, Second Version

We develop a dynamic model of opinion formation in social networks. Relevant information is spread throughout the network in such a way that no agent has enough data to learn a payoff-relevant parameter. 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, under mild assumptions, repeated interactions lead agents to successfully aggregate information and to learn the true underlying state of the world. This result holds in spite of the apparent naivite of agents’ updating rule, the agents’ need for information from sources (i.e., other agents) 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 their own views or their neighbors’ views are more accurate.

[1]  Lones Smith,et al.  Pathological Outcomes of Observational Learning , 2000 .

[2]  Alvaro Sandroni.  Necessary and Sufficient Conditions for Convergence to Nash Equilibrium: The Almost Absolute Continuity Hypothesis , 1998 .

[3]  Ronald Miller,et al.  Almost Everybody Disagrees Almost All the Time: The Genericity of Weakly Merging Nowhere , 1997 .

[4]  Valerie Isham,et al.  Non‐Negative Matrices and Markov Chains , 1983 .

[5]  Matthew O. Jackson,et al.  Naïve Learning in Social Networks and the Wisdom of Crowds , 2010 .

[6]  Douglas Gale,et al.  Bayesian learning in social networks , 2003, Games Econ. Behav..

[7]  John Nachbar.  Prediction, optimization, and learning in repeated games , 1997 .

[8]  Glenn Ellison,et al.  Rules of Thumb for Social Learning , 1993, Journal of Political Economy.

[9]  Ehud Kalai,et al.  Weak and Strong Merging of Opinions , 1994 .

[10]  Drew Fudenberg,et al.  Word-of-mouth learning , 2004, Games Econ. Behav..

[11]  S. Goyal,et al.  Conformism and diversity under social learning , 2001 .

[12]  Glenn Ellison,et al.  Word-of-Mouth Communication and Social Learning , 1995 .

[13]  Ehud Lehrer,et al.  Merging and learning , 1996 .

[14]  Asuman E. Ozdaglar,et al.  Spread of (Mis)Information in Social Networks , 2009, Games Econ. Behav..

[15]  Everett M. Rogers,et al.  Innovation Diffusion As a Spatial Process , 1967 .

[16]  Alvaro Sandroni,et al.  Supplemental Appendix for 'Non-Bayesian Updating: A Theoretical Framework' , 2008 .

[17]  Robert J. Plemmons,et al.  Nonnegative Matrices in the Mathematical Sciences , 1979, Classics in Applied Mathematics.

[18]  P. DeMarzo,et al.  Persuasion Bias, Social Influence, and Uni-Dimensional Opinions , 2001 .

[19]  Sanjeev Goyal,et al.  Learning from Neighbors , 1995 .

[20]  Geoffrey Randall.  Principles of Marketing , 1993 .

[21]  A. Whitehead.  An Introduction to Mathematics , 1949, Nature.

[22]  Alvaro Sandroni,et al.  Non-Bayesian Updating: a Theoretical Framework , 2005 .

[23]  Bryan L. Shader,et al.  Applications of Paz's inequality to perturbation bounds for Markov chains , 1998 .

[24]  Ali Jadbabaie,et al.  Non-Bayesian Social Learning , 2011, Games Econ. Behav..

[25]  Mariëlle Stoelinga,et al.  An Introduction to Probabilistic Automata , 2002, Bull. EATCS.

[26]  M. Degroot.  Reaching a Consensus , 1974 .

[27]  A. Banerjee,et al.  A Simple Model of Herd Behavior , 1992 .

[28]  S. Bikhchandani,et al.  You have printed the following article : A Theory of Fads , Fashion , Custom , and Cultural Change as Informational Cascades , 2007 .