A Monte Carlo Estimation of the Entropy for Markov Chains

  • Didier ChauveauEmail author
  • Pierre Vandekerkhove


We introduce an estimate of the entropy \(\mathbb{E}_{p^t}(\log p^t)\) of the marginal density p t of a (eventually inhomogeneous) Markov chain at time t≥1. This estimate is based on a double Monte Carlo integration over simulated i.i.d. copies of the Markov chain, whose transition density kernel is supposed to be known. The technique is extended to compute the external entropy \(\mathbb{E}_{p_1^t}(\log p^t)\), where the p 1 t s are the successive marginal densities of another Markov process at time t. We prove, under mild conditions, weak consistency and asymptotic normality of both estimators. The strong consistency is also obtained under stronger assumptions. These estimators can be used to study by simulation the convergence of p t to its stationary distribution. Potential applications for this work are presented: (1) a diagnostic by simulation of the stability property of a Markovian dynamical system with respect to various initial conditions; (2) a study of the rate in the Central Limit Theorem for i.i.d. random variables. Simulated examples are provided as illustration.


Entropy Kullback information Markov chains Stability Rate in the Central Limit Theorem 

AMS 2000 Subject Classification

62B10 60F05 60J10 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. I. A. Ahmad, and P. E. Lin, “A nonparametric estimation of the entropy for absolutely continuous distributions,” IEEE Transactions on Information Theory vol. 36 pp. 688–692, 1989.CrossRefGoogle Scholar
  2. K. Ball, F. Barthe, and A. Naor, “Entropy jumps in the presence of a spectral gap,” Duke Mathematical Journal vol. 119 no. 1 pp. 41–63, 2003.zbMATHCrossRefMathSciNetGoogle Scholar
  3. P. Del Moral, and A. Guionnet, “Central limit theorem for nonlinear filtering and interacting particle systems,” Annals of Applied Probability vol. 9 no. 2 pp. 275–297, 1999.zbMATHCrossRefMathSciNetGoogle Scholar
  4. P. Del Moral, M. Ledoux, and L. Miclo, “Contraction properties of Markov kernels,” Probability Theory and Related Fields vol. 126 pp. 395–420, 2003.zbMATHMathSciNetGoogle Scholar
  5. P. P. B. Eggermont, and V. N. LaRiccia, “Best asymptotic normality of the kernel density entropy estimator for smooth densities,” IEEE Transactions on Information Theory vol. 45 no. 4 pp. 1321–1326, 1999.zbMATHCrossRefMathSciNetGoogle Scholar
  6. D. K. Fuk, and S. V. Nagaev, “Probability inequalities for sums of independent random variables,” Theory of Probability and its Applications vol. 16 pp. 643–660, 1971; vol. 21 p. 875, 1976.Google Scholar
  7. E. L. Lehmann, Nonparametrics: Statistical Methods Based on Rank, Holden-Day Series in Probability and Statistics, McGraw-Hill: New York, 1975.Google Scholar
  8. B. Y. Levit, “Asymptotically efficient estimation of nonlinear functionals,” Problems of Information Transmission vol. 41 pp. 204–209, 1978.Google Scholar
  9. L. Miclo, “Remarques sur l’hypercontractivité et l’évolution de l’entropie des chaînes de Markov finies, Séminaire de Probabilités XXXI.” In Lecture Notes in Mathematics, pp. 136–168, Springer: Berlin Heidelberg New York, 1997.Google Scholar
  10. V. Petrov, Limit Theorems of Probability Theory, Oxford Science: Oxford, UK, 1995.zbMATHGoogle Scholar
  11. M. Seoh, and M. Hallin, “When does Edgeworth beat Berry and Esséen? Numerical evaluations of Edgeworth expansions,” Journal of Statistical Planning and Inference vol. 63 no. 1 pp. 19–38, 1997.zbMATHCrossRefMathSciNetGoogle Scholar
  12. R. J. Serfling, “Approximation theorems of mathematical statistics,” In Wiley Series in Probability and Mathematical Statistics, Wiley: New York, 1980.Google Scholar
  13. A. B. Tsybakov, and E. C. Van Der Meulen, “Root t consistent estimators of entropy for densities with unbounded support,” Scandinavian Journal of Statistics, vol. 23 pp. 75–83, 1994.Google Scholar

Copyright information

© Springer Science+Business Media, LLC 2007

Authors and Affiliations

  1. 1.Laboratoire MAPMO-UMR 6628—Fédération Denis PoissonUniversité d’OrléansOrléans Cedex 2France
  2. 2.CNRS UMR 8050Université de Marne-la-ValléeMarne-la-ValléeFrance

Personalised recommendations