Refine
Year of publication
- 1997 (1)
Document Type
- Preprint (1)
Language
- English (1) (remove)
Has Fulltext
- yes (1)
Faculty / Organisational entity
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.