| Issue |
ESAIM: PS
Volume 23, 2019
|
|
|---|---|---|
| Page(s) | 492 - 523 | |
| DOI | https://doi.org/10.1051/ps/2018017 | |
| Published online | 07 August 2019 | |
Maximum likelihood estimation in hidden Markov models with inhomogeneous noise
1
Institute for Mathematical Stochastics, Georg-August-University of Göttingen,
Goldschmidtstraße 7,
37077
Göttingen, Germany.
2
Max Planck Institute for Biophysical Chemistry,
Am Faßberg 11,
37077
Göttingen, Germany.
3
Felix-Bernstein-Institute for Mathematical Statistics in the Biosciences,
Goldschmidtstraße 7,
37077
Göttingen, Germany.
* Corresponding author: daniel.rudolf@uni-goettingen.de
Received:
11
April
2018
Accepted:
19
September
2018
We consider parameter estimation in finite hidden state space Markov models with time-dependent inhomogeneous noise, where the inhomogeneity vanishes sufficiently fast. Based on the concept of asymptotic mean stationary processes we prove that the maximum likelihood and a quasi-maximum likelihood estimator (QMLE) are strongly consistent. The computation of the QMLE ignores the inhomogeneity, hence, is much simpler and robust. The theory is motivated by an example from biophysics and applied to a Poisson- and linear Gaussian model.
Mathematics Subject Classification: 62F12 / 62M09
Key words: Inhomogeneous hidden Markov models / quasi-maximum likelihood estimation / strong consistency / robustness / asymptotic mean stationarity
© EDP Sciences, SMAI 2019
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.