Abstract
A survey of research works on the parameter estimation of hidden Markov processes is presented. Two observation models are considered: a partially observed two-dimensional Gaussian process and a telegraph process observed against the background of white Gaussian noise. The properties of estimators in the large sample and small noise asymptotics are described. Special attention is paid to the computational complexity and asymptotic efficiency of the estimators proposed.
Similar content being viewed by others
References
Bickel, P.J., Ritov, Y., and Rydén, T., Asymptotic Normality of the Maximum Likelihood Estimator for General Hidden Markov Models, Ann. Statist., 1998, vol. 26, no. 4, pp. 1614–1635.
Cappe, O., Moulines, E., and Rydén, T., Inference in Hidden Markov Models, New York: Springer, 2005.
Elliott, R.J., Aggoun, L., and Moor, J.B., Hidden Markov Models, New York: Springer, 1995.
Liptser, R.S. and Shiryaev, A.N., Statistics of Random Processes, New York: Springer, 2001, vol. 1, 2nd ed.
Fisher, R.A., Theory of Statistical Estimation, Proc. Cambridge Phylosoph. Soc., 1925, vol. 22, pp. 700–725.
Le Cam, L., On the Asymptotic Theory of Estimation and Testing Hypotheses, Proc. 3rd Berkeley Sympos., 1956, vol. I, pp. 355–368.
Kutoyants, Yu.A., Identification of Dynamical Systems with Small Noise, Dordrecht: Kluwer, 1994.
Ibragimov, I.A. and Khasminskii, R.Z., Statistical Estimation—Asymptotic Theory, New York: Springer, 1981.
Kutoyants, Yu.A. and Zhou, L., On Parameter Estimation of the Hidden Gaussian Process in Perturbed SDE. arXiv:1904.09750
Kutoyants, Yu.A., On Parameter Estimation of Hidden Ornstein—Uhlenbeck Process, J. Multivariate Anal., 2019, vol. 169, no. 1, pp. 248–263.
Liptser, R.S., On Filtration and Prediction of Components in Diffusion Markov Processes, Theory Probab. Appl., 1967, vol. 12, no. 4, pp. 697–698.
Campillo, F., Le Gland, F., and Kutoyants, Yu.A., Small Noise Asymptotics of the GLR Test for Offline Change Detection in Misspecified Diffusion Processes, Stochast. Stochast. Report., 2000, vol. 70, pp. 109–129.
Kutoyants, Yu.A., On Localization of Source by Hidden Gaussian Processes with Small Noise. Submitted, 2019. (To appear in the Annals of the Institute of Statistical Mathematics.)
Gustaffson, F., Adaptive Filtering and Change Detection, New York: Wiley, 2000.
Luo, X., GPS Stochastic Modeling, New York: Springer, 2013.
Kutoyants, Yu.A., Statistical Inference for Ergodic Diffusion Processes, London: Springer, 2004.
Kutoyants, Yu.A., Parameter Estimation for Stochastic Processes, Berlin: Heldermann, 1984.
Kallianpur, G. and Selukar, R.S., Parameter Estimation in Linear Filtering, J. Multivariate Anal., 1991, vol. 39, pp. 284–304.
Bertrand, P. and Kutoyants, Yu.A., A Minimum Distance Estimator for Partially Observed Linear Stochastic Systems, Statist. Decisions, 1996, vol. 14, pp. 323–342.
Kutoyants, Yu.A., On Parameter Estimation of Hidden Ergodic Ornstein—Uhlenbeck Process, Electronic. J. Statist., 2019, no. 13, pp. 4508–4526.
Chigansky, P., Maximum Likelihood Estimation for Hidden Markov Models in Continuous Time, Statist. Inference Stoch. Proc., 2009, vol. 12, no. 2, pp. 139–163.
Khasminskii, R.Z. and Kutoyants, Yu.A., On Parameter Estimation of Hidden Telegraph Process, Bernoulli, 2018, vol. 24, no. 3, pp. 2064–2090.
Kutoyants, Yu.A. and Pohlmann, H., Parameter Estimation for Kalman—Bucy Filter with Small Noise, Statist., 1994, no. 25, pp. 307–323.
Author information
Authors and Affiliations
Corresponding author
Additional information
This paper was recommended for publication by E. Ya. Rubinovich, a member of the Editorial Board
Russian Text © The Author(s), 2020, published in Avtomatika i Telemekhanika, 2020, No. 3, pp. 86–113.
Rights and permissions
About this article
Cite this article
Kutoyants, Y.A. Parameter Estimation for Continuous Time Hidden Markov Processes. Autom Remote Control 81, 445–468 (2020). https://doi.org/10.1134/S0005117920030054
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1134/S0005117920030054