Patterns, Types, and Bayesian Learning

Bayesian Statisticians, decision theorists, and game theorists often use Bayesian representations to describe the probability distribution governing the evolution of a stochastic process. Generally, however, one given distribution has infinitely many different Bayesian representations. This paper identifies natural, endogenous representations whose component distributions are learnable and follow patterns. Any given distribution that satisfies an asymptotic mixing condition has a unique, up to an equivalence class, natural Bayesian representation which can be obtained by conditioning on the tail-field of the process. This result follows a parallel to de Finetti's theorem, but with exchangeability weakened to asymptotic mixing which admits many more applications.

[1]  D. Fudenberg,et al.  Conditional Universal Consistency , 1999 .

[2]  Yaw Nyarko.  Bayesian learning and convergence to Nash equilibria without common priors , 1998 .

[3]  M. Jackson,et al.  Social Learning in Recurring Games , 1997 .

[4]  Ehud Lehrer,et al.  Repeated Large Games with Incomplete Information , 1997 .

[5]  Dov Samet,et al.  Common Priors and Markov Chains , 1996 .

[6]  Dov Samet.  Looking Backwards, Looking Inwards: Priors and Introspection , 1996 .

[7]  D. Bergemann,et al.  Learning and Strategic Pricing , 1996 .

[8]  Aggregation and the Law of Large Numbers in Economies with a Continuum of Agents , 1996 .

[9]  R. Marimon.  Learning from learning in economics , 1996 .

[10]  Doron Sonsino.  Learning to learn, pattern recognition, and Nash equilibrium , 1995 .

[11]  John C. Harsanyi,et al.  Games with Incomplete Information , 1994 .

[12]  Nabil I. Al-Najjar.  Factor Structures and Arbitrage Pricing in Large Asset Markets , 1994 .

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

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

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

[16]  R. Rob,et al.  Learning, Mutation, and Long Run Equilibria in Games , 1993 .

[17]  Maxwell B. Stinchcombe.  Bayesian information topologies , 1990 .

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

[19]  S. Zamir,et al.  Formulation of Bayesian analysis for games with incomplete information , 1985 .

[20]  Beth E Allen,et al.  Neighboring Information and Distributions of Agents' Characteristics Under Uncertainty , 1983 .

[21]  P. Meyer,et al.  Probabilities and potential C , 1978 .

[22]  David Blackwell,et al.  On Existence and Non-Existence of Proper, Regular, Conditional Distributions , 1975 .

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

[24]  A. Zellner.  An Introduction to Bayesian Inference in Econometrics , 1971 .

[25]  P. Billingsley,et al.  Convergence of Probability Measures , 1970, The Mathematical Gazette.

[26]  J. Harsanyi.  Games with Incomplete Information Played by 'Bayesian' Players, Part III. The Basic Probability Distribution of the Game , 1968 .

[27]  D. Blackwell,et al.  Merging of Opinions with Increasing Information , 1962 .