Berk-Nash Equilibrium: A Framework for Modeling Agents with Misspecified Models

We develop an equilibrium framework that relaxes the standard assumption that people have a correctly-specified view of their environment. Each player is characterized by a (possibly misspecified) subjective model, which describes the set of feasible beliefs over payoff-relevant consequences as a function of actions. We introduce the notion of a Berk-Nash equilibrium: Each player follows a strategy that is optimal given her belief, and her belief is restricted to be the best fit among the set of beliefs she considers possible. The notion of best fit is formalized in terms of minimizing the Kullback-Leibler divergence, which is endogenous and depends on the equilibrium strategy profile. Standard solution concepts such as Nash equilibrium and self-confirming equilibrium constitute special cases where players have correctly-specified models. We provide a learning foundation for Berk-Nash equilibrium by extending and combining results from the statistics literature on misspecified learning and the economics literature on learning in games.

[1]  L. Blume,et al.  Learning to be rational , 1982 .

[2]  Xavier Gabaix,et al.  A Sparsity-Based Model of Bounded Rationality , 2011 .

[3]  Mallesh M. Pai,et al.  Coarse decision making and overfitting , 2014, J. Econ. Theory.

[4]  R. Durrett.  Probability: Theory and Examples , 1993 .

[5]  Philippe Jehiel,et al.  Analogy-based expectation equilibrium , 2004, J. Econ. Theory.

[6]  H. White.  Maximum Likelihood Estimation of Misspecified Models , 1982 .

[7]  P. Bickel.  Efficient and Adaptive Estimation for Semiparametric Models , 1993 .

[8]  Itzhak Gilboa,et al.  Fact-Free Learning , 2004 .

[9]  J. Kagel,et al.  Common Value Auctions and the Winner's Curse , 2002 .

[10]  A. Rubinstein,et al.  Games with Procedurally Rational Players , 1997 .

[11]  M. Rabin,et al.  The Gambler's and Hot-Hand Fallacies: Theory and Applications , 2007 .

[12]  H. Kushner,et al.  Stochastic Approximation and Recursive Algorithms and Applications , 2003 .

[13]  M. Rabin.  Inference by Believers in the Law of Small Numbers , 2000 .

[14]  M. Bray.  Learning, estimation, and the stability of rational expectations , 1982 .

[15]  Dan Levin,et al.  The Origin of the Winner’s Curse: A Laboratory Study , 2007 .

[16]  J. Norris.  Appendix: probability and measure , 1997 .

[17]  D. Freedman.  On the Asymptotic Behavior of Bayes' Estimates in the Discrete Case , 1963 .

[18]  Erik Eyster,et al.  An Approach to Asset Pricing Under Incomplete and Diverse Perceptions , 2013 .

[19]  Juan F. Escobar,et al.  A Theory of Regular Markov Perfect Equilibria in Dynamic Stochastic Games: Genericity, Stability, and Purification , 2008 .

[20]  J. Tirole,et al.  Self-Confidence and Personal Motivation , 2002 .

[21]  Yaw Nyarko,et al.  Learning In Mis-Specified Models And The Possibility Of Cycles , 1991 .

[22]  O. Bunke,et al.  Asymptotic behavior of Bayes estimates under possibly incorrect models , 1998 .

[23]  M. Rabin,et al.  Financial Markets Where Traders Neglect the Informational Content of Prices , 2015, The Journal of Finance.

[24]  P. Jehiel,et al.  Valuation equilibrium , 2007 .

[25]  R. Berk,et al.  Limiting Behavior of Posterior Distributions when the Model is Incorrect , 1966 .

[26]  R. Selten.  Reexamination of the perfectness concept for equilibrium points in extensive games , 1975, Classics in Game Theory.

[27]  E. Kalai,et al.  Rational Learning Leads to Nash Equilibrium , 1993 .

[28]  D. Pollard.  A User's Guide to Measure Theoretic Probability by David Pollard , 2001 .

[29]  M. Benaïm.  Dynamics of stochastic approximation algorithms , 1999 .

[30]  J. Kagel,et al.  The Winner's Curse and Public Information in Common Value Auctions: Comment , 1999 .

[31]  Dan Levin,et al.  Can Relaxation of Beliefs Rationalize the Winner's Curse?: An Experimental Study , 2010 .

[32]  D. Freedman,et al.  On the consistency of Bayes estimates , 1986 .

[33]  David M. Kreps,et al.  Learning Mixed Equilibria , 1993 .

[34]  R. A. Leibler,et al.  On Information and Sufficiency , 1951 .

[35]  M. Rothschild.  A two-armed bandit theory of market pricing , 1974 .

[36]  A. Rubinstein.  Finite automata play the repeated prisoner's dilemma , 1986 .

[37]  D. Fudenberg,et al.  Self-confirming equilibrium , 1993 .

[38]  J. Jordan.  Three Problems in Learning Mixed-Strategy Nash Equilibria , 1993 .

[39]  Yuval Salant,et al.  Procedural Analysis of Choice Rules with Applications to Bounded Rationality , 2011 .

[40]  Andrea Wilson.  Bounded Memory and Biases in Information Processing , 2014 .

[41]  Philippe Jehiel.  Limited horizon forecast in repeated alternate games , 1995 .

[42]  D. Fudenberg,et al.  Learning and Equilibrium , 2009 .

[43]  T. Sargent.  Bounded rationality in macroeconomics , 1993 .

[44]  Ran Spiegler,et al.  The market for quacks , 2006 .

[45]  Drew Fudenberg,et al.  Learning to Play Bayesian Games , 2001, Games Econ. Behav..

[46]  Drew Fudenberg,et al.  Learning, Experimentation and Equilibrium in Games , 2010 .

[47]  Kenneth J. Arrow,et al.  Notes on Expectations Equilibria in Bayesian Settings Institute for Mathematical Studies in the Social Sciences , 1973 .

[48]  N. Kiefer,et al.  Controlling a Stochastic Process with Unknown Parameters , 1988 .

[49]  J. Harsanyi.  Games with randomly disturbed payoffs: A new rationale for mixed-strategy equilibrium points , 1973 .

[50]  C. Stein.  A bound for the error in the normal approximation to the distribution of a sum of dependent random variables , 1972 .

[51]  D. Fudenberg,et al.  Steady state learning and Nash equilibrium , 1993 .

[52]  Ignacio Esponda.  Behavioral Equilibrium in Economies with Adverse Selection , 2008 .

[53]  Yaw Nyarko,et al.  On the convexity of the value function in Bayesian optimal control problems , 1994 .

[54]  Ignacio Esponda,et al.  Learning foundation for equilibrium in voting environments with private information∗ , 2011 .

[55]  Joshua Schwartzstein.  SELECTIVE ATTENTION AND LEARNING , 2014 .

[56]  Xavier Gabaix,et al.  Game Theory with Sparsity-Based Bounded Rationality ∗ , 2011 .

[57]  M. Hirsch,et al.  Differential Equations, Dynamical Systems, and an Introduction to Chaos , 2003 .

[58]  G. Evans,et al.  Learning and expectations in macroeconomics , 2001 .

[59]  Philippe Jehiel,et al.  Revisiting games of incomplete information with analogy-based expectations , 2008, Games Econ. Behav..

[60]  Kim C. Border,et al.  Infinite Dimensional Analysis: A Hitchhiker’s Guide , 1994 .

[61]  Ariel Rubinstein,et al.  Modeling the Economic Interaction of Agents With Diverse Abilities to Recognize Equilibrium Patterns , 2003 .

[62]  M. Hirsch,et al.  Mixed Equilibria and Dynamical Systems Arising from Fictitious Play in Perturbed Games , 1999 .

[63]  Massimo Marinacci,et al.  Selfcon…rming Equilibrium and Model Uncertainty , 2012 .

[64]  T. Sargent.  The Conquest of American Inflation , 1999 .

[65]  A. McLennan.  Price dispersion and incomplete learning in the long run , 1984 .

[66]  P. Jehiel.  Learning to Play Limited Forecast Equilibria , 1998 .

[67]  William H. Sandholm,et al.  ON THE GLOBAL CONVERGENCE OF STOCHASTIC FICTITIOUS PLAY , 2002 .

[68]  A. Kirman.  Learning by Firms about Demand Conditions , 1975 .

[69]  Eld,et al.  Cursed Equilibrium , 2000 .

[70]  Ignacio Esponda,et al.  Hypothetical Thinking and Information Extraction in the Laboratory , 2014 .

[71]  Nabil I. Al-Najjar.  Decision Makers as Statisticians: Diversity, Ambiguity, and Learning , 2009 .

[72]  Drew Fudenberg,et al.  Learning in extensive-form games I. Self-confirming equilibria , 1995 .

[73]  Daniel Kahneman,et al.  Availability: A heuristic for judging frequency and probability , 1973 .

[74]  R. Spiegler.  Bounded Rationality and Industrial Organization , 2011 .

[75]  Nicholas Barberis,et al.  A Model of Investor Sentiment , 1997 .

[76]  A. Rubinstein,et al.  Rationalizable Conjectural Equilibrium: Between Nash and Rationalizability , 1994 .

[77]  N. Barberis,et al.  A Model of Investor Sentiment , 1997 .

[78]  R. Spiegler.  Placebo Reforms † , 2013 .

[79]  Andrew Postlewaite,et al.  Confidence-Enhanced Performance , 2001 .

[80]  R. Spiegler.  Bayesian Networks and Boundedly Rational Expectations , 2014 .

[81]  D. Fudenberg,et al.  The Theory of Learning in Games , 1998 .

[82]  R. M. Dudley,et al.  Real Analysis and Probability , 1989 .

[83]  Joel Sobel,et al.  Non-linear prices and price-taking behavior , 1984 .