Abstract
We generalize asymptotic properties obtained in the observation-driven times series models considered by [R. Douc, P. Doukhan, and E. Moulines, Ergodicity of observation-driven time series models and consistency of the maximum likelihood estimator, Stochastic Processes Appl., 123(7):2620–2647, 2013] in the sense that the conditional law of each observation is also permitted to depend on the parameter. The existence of ergodic solutions and the consistency of the maximum likelihood estimator (MLE) are derived under easy-to-check conditions. The obtained conditions appear to apply for a wide class of models. We illustrate our results with specific observation-driven times series, including the recently introduced NBIN-GARCH and NM-GARCH models, demonstrating the consistency of the MLE for these two models.
Similar content being viewed by others
References
C. Alexander and E. Lazar, Normal mixture GARCH(1, 1): Applications to exchange rate modelling, J. Appl. Econom., 21(3):307–336, 2006, doi:10.1002/jae.849.
T. Bollerslev, Generalized autoregressive conditional heteroskedasticity, J. Econom., 31(3):307–327, 1986, doi:10.1016/0304-4076(86)90063-1.
T. Bollerslev, Glossary to ARCH (GARCH), CREATES Research Papers 2008-49, School of Economics and Management, University of Aarhus, 2008, available from: http://ideas.repec.org/p/aah/create/2008-49.html.
D.R. Cox, Statistical analysis of time series: Some recent developments, Scand. J. Stat., 8(2):93–115, 1981. With discussion by G. Gudmundsson, G. Lindgren, L. Bondesson, E. Harsaae, P. Laake, K. Juselius, and S.L. Lauritzen, with a reply by the author.
R.A. Davis,W.T. Dunsmuir, and S.B. Streett, Observation-driven models for Poisson counts, Biometrika, 90(4):777–790, 2003, doi:10.1093/biomet/90.4.777.
R.A. Davis and H. Liu, Theory and inference for a class of observation-driven models with application to time series of counts, 2012, available from: http://adsabs.harvard.edu/abs/2012arXiv1204.3915D.
R. Douc, P. Doukhan, and E. Moulines, Ergodicity of observation-driven time series models and consistency of the maximum likelihood estimator, Stochastic Processes Appl., 123(7):2620–2647, 2013, doi:10.1016/j.spa.2013.04.010.
R. Douc, F. Roueff, and T. Sim, The maximizing set of the asymptotic normalized log-likelihood for partially observedMarkov chains, 2014 (submitted for publication).
P. Doukhan, K. Fokianos, and D. Tjøstheim, On weak dependence conditions for Poisson autoregressions, Stat. Probab. Lett., 82(5):942–948, 2012, doi:10.1016/j.spl.2012.01.015.
K. Fokianos, A. Rahbek, and D. Tjøstheim, Poisson autoregression, J. Am. Stat. Assoc., 104(488):1430–1439, 2009, doi:10.1198/jasa.2009.tm08270.
K. Fokianos and D. Tjøstheim, Log-linear Poisson autoregression, J. Multivariate Anal., 102(3):563–578, 2011, doi:10.1016/j.jmva.2010.11.002.
M. Haas, S. Mittnik, and M.S. Paolella, Mixed normal conditional heteroskedasticity, Journal of Financial Econometrics, 2(2):211–250, 2004, doi:10.1093/jjfinec/nbh009.
B.G. Leroux, Maximum-likelihood estimation for hidden Markov models, Stochastic Processes Appl., 40(1):127–143, 1992, doi:10.1016/0304-4149(92)90141-C.
S. Meyn and R.L. Tweedie, Markov Chains and Stochastic Stability, 2nd ed., Cambridge Univ. Press, Cambridge, 2009, doi:10.1017/CBO9780511626630.With a prologue by Peter W. Glynn.
E. Moulines, P. Priouret, and F. Roueff, On recursive estimation for time varying autoregressive processes, Ann. Stat., 33(6):2610–2654, 2005, doi:10.1214/009053605000000624.
M.H. Neumann, Absolute regularity and ergodicity of Poisson count processes, Bernoulli, 17(4):1268–1284, 2011, doi:10.3150/10-BEJ313.
J. Pfanzagl, On the measurability and consistency of minimum contrast estimates, Metrika, 14:249–272, 1969, available from: http://eudml.org/doc/175401.
S.B. Streett, SomeObservation Driven Models for Time Series, PhD thesis, Colorado State University, 2000, available from: http://search.proquest.com/docview/249974599.
D.B. Woodard, D.S. Matteson, and S.G. Henderson, Stationarity of generalized autoregressive moving average models, Electron. J. Stat., 5:800–828, 2011, doi:10.1214/11-EJS627.
F. Zhu, A negative binomial integer-valued GARCH model, J. Time Ser. Anal., 32(1):54–67, 2011, doi:10.1111/j.1467-9892.2010.00684.x.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Douc, R., Roueff, F. & Sim, T. Handy sufficient conditions for the convergence of the maximum likelihood estimator in observation-driven models. Lith Math J 55, 367–392 (2015). https://doi.org/10.1007/s10986-015-9286-8
Received:
Revised:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10986-015-9286-8