dc.contributor.author | Tomala, Tristan | |
dc.contributor.author | Gossner, Olivier | |
dc.date.accessioned | 2011-05-12T10:13:47Z | |
dc.date.available | 2011-05-12T10:13:47Z | |
dc.date.issued | 2006 | |
dc.identifier.uri | https://basepub.dauphine.fr/handle/123456789/6267 | |
dc.language.iso | en | en |
dc.subject | Stochastic process | en |
dc.subject | signals | en |
dc.subject | entropy | en |
dc.subject | repeated games | en |
dc.subject.ddc | 519 | en |
dc.title | Empirical Distributions of Beliefs Under Imperfect Observation | en |
dc.type | Article accepté pour publication ou publié | |
dc.description.abstracten | Let (xn)n be a process with values in a finite set X and law P, and let yn = f(xn) be a function of the process. At stage n, the conditional distribution pn = P(xn | x1,...,xn–1), element of {Pi} = {Delta}(X), is the belief that a perfect observer, who observes the process online, holds on its realization at stage n. A statistician observing the signals y1,...,yn holds a belief en = P(pn | x1,...,xn) isin {Delta}({Pi}) on the possible predictions of the perfect observer. Given X and f, we characterize the set of limits of expected empirical distributions of the process (en) when P ranges over all possible laws of (xn)n. | en |
dc.relation.isversionofjnlname | Mathematics of Operations Research | |
dc.relation.isversionofjnlvol | 31 | en |
dc.relation.isversionofjnlissue | 1 | en |
dc.relation.isversionofjnldate | 2006 | |
dc.relation.isversionofjnlpages | 13-30 | en |
dc.relation.isversionofdoi | http://dx.doi.org/10.1287/moor.1050.0174 | en |
dc.description.sponsorshipprivate | oui | en |
dc.relation.isversionofjnlpublisher | Informs | en |
dc.subject.ddclabel | Probabilités et mathématiques appliquées | en |