Patterns, Types, and Bayesian Learning

Matthew O. Jackson (), Ehud Kalai and Rann Smorodinsky
Additional contact information
Rann Smorodinsky: Technion

Game Theory and Information from EconWPA

Abstract: 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.

Keywords: patterns; asymptotic mixing; types; Bayesian learning; stochastic processes (search for similar items in EconPapers)
JEL-codes: C73 C11 D83 (search for similar items in EconPapers)
Date: Written
Note: Type of Document - postscript; prepared on gateway e 3100; to print on postscript; pages: 27 ; figures: none. comments welcome
View list of references

Downloads: (external link)
http://129.3.20.41/eps/game/papers/9711/9711002.ps.gz (application/postscript)
http://129.3.20.41/eps/game/papers/9711/9711002.pdf (application/pdf)

Related works:
Working Paper: Patterns, Types, and Bayesian Learning (1997)
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: http://EconPapers.repec.org/RePEc:wpa:wuwpga:9711002

Access Statistics for this paper

More papers in Game Theory and Information from EconWPA
Series data maintained by EconWPA ().