DocumentCode
3010161
Title
Convergence rates of the maximum likelihood estimator of hidden Markov models
Author
Mevel, Laurent ; Finesso, Lorenzo
Author_Institution
IRISA/INRIA, Rennes, France
Volume
5
fYear
2000
fDate
2000
Firstpage
4691
Abstract
We derive the almost sure rate of convergence of the maximum likelihood estimator of the parameters of a hidden Markov model with continuous observations and finite state space. The analysis is based on the geometric ergodicity properties of the prediction filter and its derivatives. As an example of application of these results we prove that, also in this context, the likelihood ratio is a consistent statistic for model selection
Keywords
convergence; filtering theory; hidden Markov models; matrix algebra; maximum likelihood estimation; prediction theory; probability; almost sure convergence rate; continuous observations; finite state space; geometric ergodicity properties; likelihood ratio; model selection; prediction filter; Context modeling; Convergence; Filters; Hidden Markov models; Maximum likelihood estimation; Parameter estimation; Probability distribution; State estimation; State-space methods; Statistics;
fLanguage
English
Publisher
ieee
Conference_Titel
Decision and Control, 2000. Proceedings of the 39th IEEE Conference on
Conference_Location
Sydney, NSW
ISSN
0191-2216
Print_ISBN
0-7803-6638-7
Type
conf
DOI
10.1109/CDC.2001.914668
Filename
914668
Link To Document