On Risk Rates and Large Deviations in Finite Markov Chain Experiments

  • The observation of an ergodic Markov chain asymptotically allows perfect identification of the transition matrix. In this paper we determine the rate of the information contained in the first n observations, provided the unknown transition matrix belongs to a known finite set. As an essential tool we prove new refinements of the large deviation theory of the empirical pair measure of finite Markov chains. Keywords: Markov Chain, Entropy, Bayes risk, Large Deviations.

Export metadata

  • Export Bibtex
  • Export RIS

Additional Services

Share in Twitter Search Google Scholar
Metadaten
Author:Peter Scheffel, Heinrich von Weizsäcker
URN (permanent link):urn:nbn:de:hbz:386-kluedo-7349
Document Type:Preprint
Language of publication:English
Year of Completion:1997
Year of Publication:1997
Publishing Institute:Technische Universität Kaiserslautern
Source:Math. Meth. Statistics 3, 1997, Seiten 293-312
Faculties / Organisational entities:Fachbereich Mathematik
DDC-Cassification:510 Mathematik

$Rev: 12793 $