IDEAS home Printed from https://ideas.repec.org/a/eee/csdana/v52y2008i9p4147-4160.html
   My bibliography  Save this article

Direct maximization of the likelihood of a hidden Markov model

Author

Listed:
  • Turner, Rolf

Abstract

Ever since the introduction of hidden Markov models by Baum and his co-workers, the method of choice for fitting such models has been maximum likelihood via the EM algorithm. In recent years it has been noticed that the gradient and Hessian of the log likelihood of hidden Markov and related models may be calculated in parallel with a filtering process by which the likelihood may be calculated. Various authors have used, or suggested the use of, this idea in order to maximize the likelihood directly, without using the EM algorithm. In this paper we discuss an implementation of such an approach. We have found that a straightforward implementation of Newton's method sometimes works but is unreliable. A form of the Levenberg-Marquardt algorithm appears to provide excellent reliability. Two rather complex examples are given for applying this algorithm to the fitting of hidden Markov models. In the first a better than 6-fold increase in speed over the EM algorithm was achieved. The second example turned out to be problematic (somewhat interestingly) in that the maximum likelihood estimator appears to be inconsistent. Whatever its merit, this estimator is calculated much faster by Levenberg-Marquardt than by EM. We also compared the Levenberg-Marquardt algorithm, applied to the first example, with a generic numerical maximization procedure. The Levenberg-Marquardt algorithm appeared to perform almost three times better than the generic procedure, even when analytic derivatives were provided, and 19 times better when they were not provided.

Suggested Citation

  • Turner, Rolf, 2008. "Direct maximization of the likelihood of a hidden Markov model," Computational Statistics & Data Analysis, Elsevier, vol. 52(9), pages 4147-4160, May.
  • Handle: RePEc:eee:csdana:v:52:y:2008:i:9:p:4147-4160
    as

    Download full text from publisher

    File URL: http://www.sciencedirect.com/science/article/pii/S0167-9473(08)00020-0
    Download Restriction: Full text for ScienceDirect subscribers only.
    ---><---

    As the access to this document is restricted, you may want to search for a different version of it.

    References listed on IDEAS

    as
    1. Leroux, Brian G., 1992. "Maximum-likelihood estimation for hidden Markov models," Stochastic Processes and their Applications, Elsevier, vol. 40(1), pages 127-143, February.
    2. D. Oakes, 1999. "Direct calculation of the information matrix via the EM," Journal of the Royal Statistical Society Series B, Royal Statistical Society, vol. 61(2), pages 479-482, April.
    3. Campillo, Fabien & Le Gland, François, 1989. "MLE for partially observed diffusions: direct maximization vs. the em algorithm," Stochastic Processes and their Applications, Elsevier, vol. 33(2), pages 245-274, December.
    Full references (including those not matched with items on IDEAS)

    Citations

    Citations are extracted by the CitEc Project, subscribe to its RSS feed for this item.
    as


    Cited by:

    1. Ari Hyytinen & Frode Steen & Otto Toivanen, 2018. "Cartels Uncovered," American Economic Journal: Microeconomics, American Economic Association, vol. 10(4), pages 190-222, November.
    2. Forcina, Antonio, 2017. "A Fisher-scoring algorithm for fitting latent class models with individual covariates," Econometrics and Statistics, Elsevier, vol. 3(C), pages 132-140.
    3. Maruotti, Antonello & Punzo, Antonio, 2017. "Model-based time-varying clustering of multivariate longitudinal data with covariates and outliers," Computational Statistics & Data Analysis, Elsevier, vol. 113(C), pages 475-496.
    4. Gordon Anderson & Alessio Farcomeni & Maria Grazia Pittau & Roberto Zelli, 2019. "Rectangular latent Markov models for time‐specific clustering, with an analysis of the wellbeing of nations," Journal of the Royal Statistical Society Series C, Royal Statistical Society, vol. 68(3), pages 603-621, April.
    5. Bartolucci, Francesco & Montanari, Giorgio E. & Pandolfi, Silvia, 2015. "Three-step estimation of latent Markov models with covariates," Computational Statistics & Data Analysis, Elsevier, vol. 83(C), pages 287-301.
    6. Gordon Anderson & Alessio Farcomeni & Grazia Pittau & Roberto Zelli, 2017. "Rectangular latent Markov models for time-specific clustering," Working Papers tecipa-589, University of Toronto, Department of Economics.
    7. F. Bartolucci & A. Farcomeni & F. Pennoni, 2014. "Latent Markov models: a review of a general framework for the analysis of longitudinal data with covariates," TEST: An Official Journal of the Spanish Society of Statistics and Operations Research, Springer;Sociedad de Estadística e Investigación Operativa, vol. 23(3), pages 433-465, September.
    8. Simon DeDeo & David C Krakauer & Jessica C Flack, 2010. "Inductive Game Theory and the Dynamics of Animal Conflict," PLOS Computational Biology, Public Library of Science, vol. 6(5), pages 1-16, May.
    9. Pereira, Diogo & Nunes, Cláudia & Rodrigues, Rui, 2024. "A new algorithm for inference in HMM's with lower span complexity," Computational Statistics & Data Analysis, Elsevier, vol. 195(C).
    10. Elliott, Robert J. & Chen, Zhiping & Duan, Qihong, 2009. "Insurance claims modulated by a hidden Brownian marked point process," Insurance: Mathematics and Economics, Elsevier, vol. 45(2), pages 163-172, October.
    11. Iain L. MacDonald, 2014. "Numerical Maximisation of Likelihood: A Neglected Alternative to EM?," International Statistical Review, International Statistical Institute, vol. 82(2), pages 296-308, August.
    12. Bartolucci, Francesco & Bacci, Silvia & Mira, Antonietta, 2018. "On the role of latent variable models in the era of big data," Statistics & Probability Letters, Elsevier, vol. 136(C), pages 165-169.

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Shu Yang & Jae Kwang Kim, 2016. "Likelihood-based Inference with Missing Data Under Missing-at-Random," Scandinavian Journal of Statistics, Danish Society for Theoretical Statistics;Finnish Statistical Society;Norwegian Statistical Association;Swedish Statistical Association, vol. 43(2), pages 436-454, June.
    2. María Luz Gámiz & Nikolaos Limnios & Mari Carmen Segovia-García, 2023. "The continuous-time hidden Markov model based on discretization. Properties of estimators and applications," Statistical Inference for Stochastic Processes, Springer, vol. 26(3), pages 525-550, October.
    3. Ahmed Belhadjayed & Grégoire Loeper & Frédéric Abergel, 2016. "Forecasting Trends With Asset Prices," Post-Print hal-01512431, HAL.
    4. Aknouche, Abdelhakim & Dimitrakopoulos, Stefanos, 2020. "On an integer-valued stochastic intensity model for time series of counts," MPRA Paper 105406, University Library of Munich, Germany.
    5. Zhou, Lin & Tang, Yayong, 2021. "Linearly preconditioned nonlinear conjugate gradient acceleration of the PX-EM algorithm," Computational Statistics & Data Analysis, Elsevier, vol. 155(C).
    6. Björn Andersson & Tao Xin, 2021. "Estimation of Latent Regression Item Response Theory Models Using a Second-Order Laplace Approximation," Journal of Educational and Behavioral Statistics, , vol. 46(2), pages 244-265, April.
    7. Genon-Catalot, Valentine, 2003. "A non-linear explicit filter," Statistics & Probability Letters, Elsevier, vol. 61(2), pages 145-154, January.
    8. Jörn Dannemann & Hajo Holzmann, 2008. "Likelihood Ratio Testing for Hidden Markov Models Under Non‐standard Conditions," Scandinavian Journal of Statistics, Danish Society for Theoretical Statistics;Finnish Statistical Society;Norwegian Statistical Association;Swedish Statistical Association, vol. 35(2), pages 309-321, June.
    9. Massimo Guidolin, 2013. "Markov switching models in asset pricing research," Chapters, in: Adrian R. Bell & Chris Brooks & Marcel Prokopczuk (ed.), Handbook of Research Methods and Applications in Empirical Finance, chapter 1, pages 3-44, Edward Elgar Publishing.
    10. Anton Molyboha & Michael Zabarankin, 2012. "Stochastic Optimization of Sensor Placement for Diver Detection," Operations Research, INFORMS, vol. 60(2), pages 292-312, April.
    11. Pierre Guérin & Danilo Leiva-Leon & Massimiliano Marcellino, 2020. "Markov-Switching Three-Pass Regression Filter," Journal of Business & Economic Statistics, Taylor & Francis Journals, vol. 38(2), pages 285-302, April.
    12. Giorgio Eduardo Montanari & Marco Doretti & Maria Francesca Marino, 2022. "Model-based two-way clustering of second-level units in ordinal multilevel latent Markov models," Advances in Data Analysis and Classification, Springer;German Classification Society - Gesellschaft für Klassifikation (GfKl);Japanese Classification Society (JCS);Classification and Data Analysis Group of the Italian Statistical Society (CLADAG);International Federation of Classification Societies (IFCS), vol. 16(2), pages 457-485, June.
    13. Bacci, Silvia & Bartolucci, Francesco & Pieroni, Luca, 2012. "A causal analysis of mother’s education on birth inequalities," MPRA Paper 38754, University Library of Munich, Germany.
    14. Poncela, Pilar & Ruiz, Esther & Miranda, Karen, 2021. "Factor extraction using Kalman filter and smoothing: This is not just another survey," International Journal of Forecasting, Elsevier, vol. 37(4), pages 1399-1425.
    15. David Aristei & Silvia Bacci & Francesco Bartolucci & Silvia Pandolfi, 2021. "A bivariate finite mixture growth model with selection," Advances in Data Analysis and Classification, Springer;German Classification Society - Gesellschaft für Klassifikation (GfKl);Japanese Classification Society (JCS);Classification and Data Analysis Group of the Italian Statistical Society (CLADAG);International Federation of Classification Societies (IFCS), vol. 15(3), pages 759-793, September.
    16. Linda Möstel & Marius Pfeuffer & Matthias Fischer, 2020. "Statistical inference for Markov chains with applications to credit risk," Computational Statistics, Springer, vol. 35(4), pages 1659-1684, December.
    17. Mogens Bladt & Michael SØrensen, 2009. "Efficient estimation of transition rates between credit ratings from observations at discrete time points," Quantitative Finance, Taylor & Francis Journals, vol. 9(2), pages 147-160.
    18. Aknouche, Abdelhakim & Dimitrakopoulos, Stefanos & Touche, Nassim, 2019. "Integer-valued stochastic volatility," MPRA Paper 91962, University Library of Munich, Germany, revised 04 Feb 2019.
    19. Ahmed Bel Hadj Ayed & Gr'egoire Loeper & Fr'ed'eric Abergel, 2015. "Forecasting trends with asset prices," Papers 1504.03934, arXiv.org, revised Apr 2015.
    20. Li, Yong & Zeng, Tao & Yu, Jun, 2014. "A new approach to Bayesian hypothesis testing," Journal of Econometrics, Elsevier, vol. 178(P3), pages 602-612.

    More about this item

    Statistics

    Access and download statistics

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:eee:csdana:v:52:y:2008:i:9:p:4147-4160. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: Catherine Liu (email available below). General contact details of provider: http://www.elsevier.com/locate/csda .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.