Hostname: page-component-848d4c4894-tn8tq Total loading time: 0 Render date: 2024-07-02T08:49:06.115Z Has data issue: false hasContentIssue false
  • English
  • Français

Large deviations and the Bayesian estimation of higher-order Markov transition functions

Part of: Inference from stochastic processes Limit theorems Markov processes Parametric inference

Published online by Cambridge University Press:  14 July 2016

F. Papangelou
F. Papangelou*
Affiliation:
University of Manchester
*
∗Postal address: Department of Mathematics, University of Manchester, Oxford Road, Manchester, M13 9PL, UK.
Get access Rights & Permissions [Opens in a new window]

Abstract

In the Bayesian estimation of higher-order Markov transition functions on finite state spaces, a prior distribution may assign positive probability to arbitrarily high orders. If there are n observations available, we show (for natural priors) that, with probability one, as n → ∞ the Bayesian posterior distribution ‘discriminates accurately' for orders up to β log n, if β is smaller than an explicitly determined β0. This means that the ‘large deviations' of the posterior are controlled by the relative entropies of the true transition function with respect to all others, much as the large deviations of the empirical distributions are governed by their relative entropies with respect to the true transition function. An example shows that the result can fail even for orders β log n if β is large.

Keywords

MARKOV CHAINSHIGHER-ORDER TRANSITION FUNCTIONSRELATIVE ENTROPYLARGE DEVIATIONSPOSTERIOR DISTRIBUTIONSEXPONENTIAL DECAY

MSC classification

Primary: 60F10: Large deviations 60F15: Strong theorems
Secondary: 60J10: Markov chains (discrete-time Markov processes on discrete state spaces) 62F15: Bayesian inference 62M05: Markov processes
Type
Research Papers
Information
Journal of Applied Probability , Volume 33 , Issue 1 , March 1996 , pp. 18 - 27
Copyright
Copyright © Applied Probability Trust 1996 

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

References

Bahadur, R. R. and Raghavachari, M. (1972) Some asymptotic properties of likelihood ratios on general sample spaces. Proc. 6th Berkeley Symp. on Mathematical Statistics and Probability, Vol. I. pp. 129–152. University of California Press, Berkeley.Google Scholar
Csiszár, I. (1967) Information-type measures of difference of probability distributions and indirect observations. Studia Sci. Math. Hungar. 2, 299–318.Google Scholar
Davisson, L. D., Longo, G. and Sgarro, A. (1981) The error exponent for the noiseless encoding of finite ergodic Markov sources. IEEE Trans. Inform. Theory 27, 431–438.Google Scholar
Dembo, A. and Zeitouni, O. (1993) Large Deviations Techniques and Applications. Jones and Bartlett, Boston.Google Scholar
Diaconis, P. and Freedman, D. (1986) On the consistency of Bayes estimates. Ann. Statist. 14, 1–67.Google Scholar
Ellis, R. S. (1988) Large deviations for the empirical measure of a Markov chain with an application to the multivariate empirical measure. Ann. Prob. 16, 1496–1508.CrossRefGoogle Scholar
Freedman, D. A. (1963) On the asymptotic behaviour of Bayes' estimates in the discrete case. Ann. Math. Statist. 34, 1386–1403.Google Scholar
Merhav, N., Gutman, M. and Ziv, J. (1989) On the estimation of the order of a Markov chain and universal data compression. IEEE Trans. Inform. Theory 35, 1014–1019.Google Scholar