Electronic Journal of Statistics

Asymptotic properties of quasi-maximum likelihood estimators in observation-driven time series models

Randal Douc, Konstantinos Fokianos, and Eric Moulines

Full-text: Open access


We study a general class of quasi-maximum likelihood estimators for observation-driven time series models. Our main focus is on models related to the exponential family of distributions like Poisson based models for count time series or duration models. However, the proposed approach is more general and covers a variety of time series models including the ordinary GARCH model which has been studied extensively in the literature. We provide general conditions under which quasi-maximum likelihood estimators can be analyzed for this class of time series models and we prove that these estimators are consistent and asymptotically normally distributed regardless of the true data generating process. We illustrate our results using classical examples of quasi-maximum likelihood estimation including standard GARCH models, duration models, Poisson type autoregressions and ARMA models with GARCH errors. Our contribution unifies the existing theory and gives conditions for proving consistency and asymptotic normality in a variety of situations.

Article information

Electron. J. Statist. Volume 11, Number 2 (2017), 2707-2740.

Received: April 2016
First available in Project Euclid: 4 July 2017

Permanent link to this document

Digital Object Identifier

Zentralblatt MATH identifier

Primary: 62M10: Time series, auto-correlation, regression, etc. [See also 91B84] 60J05: Discrete-time Markov processes on general state spaces
Secondary: 62M05: Markov processes: estimation

Asymptotic normality consistency count time series duration models GARCH models Kullback-Leibler divergence maximum likelihood stationarity

Creative Commons Attribution 4.0 International License.


Douc, Randal; Fokianos, Konstantinos; Moulines, Eric. Asymptotic properties of quasi-maximum likelihood estimators in observation-driven time series models. Electron. J. Statist. 11 (2017), no. 2, 2707--2740. doi:10.1214/17-EJS1299. https://projecteuclid.org/euclid.ejs/1499133752

Export citation


  • [1] Ahmad, A. and Franq, C. (2016). Poisson QMLE of count time series, models.J. Time Ser. Anal., 291–314.
  • [2] Bardet, J.-M. and Wintenberger, O. (2010). Asymptotic normality of the quasi-maximum likelihood estimator for multidimensional causal, processes.Ann. Statist.37, 2730–2759.
  • [3] Berkes, I. and Horváth, L. (2004). The efficiency of the estimators of the parameters in GARCH, processes.Ann. Statist.32, 633–655.
  • [4] Berkes, I., Horváth, L., and Kokoszka, P. (2003). GARCH processes: structure and, estimation.Bernoulli9, 201–227.
  • [5] Billingsley, P. (1961). The Lindeberg-Levy theorem for, martingales.Proceedings of the American Mathematical Society12, 5, 788–792.
  • [6] Bollerslev, T. (1986). Generalized autoregressive conditional, heteroskedasticity.J. Econometrics31, 307–327.
  • [7] Bougerol, P. and Picard, N. (1992). Strict stationarity of generalized autoregressive, processes.Ann. Prob.20, 1714–1729.
  • [8] Christou, V. and Fokianos, K. (2014). Quasi–likelihood inference for negative binomial time series, models.J. Time Ser. Anal.35, 55–78.
  • [9] Cox, D. (1981). Statistical analysis of time-series: some recent, developments.Scand. J. Statist.8, 93–115.
  • [10] Davis, R., Dunsmuir, W., and Streett, S. (2003). Observation-driven models for Poisson, counts.Biometrika90, 777–790.
  • [11] Douc, R., Doukhan, P., and Moulines, E. (2013). Ergodicity of observation-driven time series models and consistency of the maximum likelihood, estimator.Stochastic Process. Appl.123, 2620–2647.
  • [12] Douc, R., Moulines, E., and Stoffer, D., (2014).Nonlinear Time Series: Theory, Methods and Applications with R Examples. CRC Press.
  • [13] Engle, R. F. (2000). The econometrics of ultra-high-frequency, data.Econometrica68, 1–22.
  • [14] Engle, R. F. and Russell, J. R. (1998). Autoregressive conditional duration: a new model for irregularly spaced transaction, data.Econometrica66, 1127–1162.
  • [15] Fan, J., Qi, L., and Xiu, D. (2014). Quasi-Maximum likelihood estimation of GARCH models with heavy-tailed, likelihoods.J. Bus. Econ. Statist.32, 178–191. with discussion.
  • [16] Ferland, R., Latour, A., and Oraichi, D. (2006). Integer-valued GARCH, process.J. Time Ser. Anal.27, 923–942.
  • [17] Fokianos, K. (2012). Count time series models., InHandbook of Statistics: Time Series Analysis–Methods and Applications, T. S. Rao, S. S. Rao, and C. R. Rao, Eds. Vol.30. Elsevier B. V., Amsterdam, 315–347.
  • [18] Fokianos, K., Rahbek, A., and Tjøstheim, D. (2009). Poisson, autoregression.J. Am. Statist. Assoc.104, 1430–1439.
  • [19] Fokianos, K. and Tjøstheim, D. (2011). Log-linear poisson, autoregression.J. of Multivariate Analysis102, 563–578.
  • [20] Francq, C. and Zakoian, J.-M. (2004). Maximum likelihood estimation of pure garch and arma-garch, processes.Bernoulli10, 605–637.
  • [21] Francq, C. and Zakoïan, J.-M., (2010).GARCH models: Structure, Statistical Inference and Financial Applications. Wiley, United Kingdom.
  • [22] Francq, C. and Zakoïan, J.-M. (2015). Risk-parameter estimation in volatility, models.Journal of Econometrics184, 158–173.
  • [23] Godambe, V. P., (1991).Estimating Functions. Oxford Science Publications, Oxford.
  • [24] Hautsch, N. (2012). Univariate multiplicative error models., InEconometrics of Financial High-Frequency Data. Springer Berlin Heidelberg, 99–142.
  • [25] Heyde, C. C., (1997).Quasi-Likelihood and its Applications: A General Approach to Optimal Parameter Estimation. Springer, New York.
  • [26] Jensen, S. T. and Rahbek, A. (2004). Asymptotic normality of the QMLE estimator of ARCH in the nonstationary, case.Econometrica72, 641–646.
  • [27] Kauppi, H. and Saikkonen, P. (2008). Predicting US recessions with dynamic binary response, models.The Review of Economics and Statistics90, 777–791.
  • [28] Koopman, S. J. (1993). Disturbance smoother for state space, models.Biometrika80, 117–126.
  • [29] Lee, S. and Hansen, B. (1994). Asymptotic theory for the GARCH(1,1) quasi–maximum likelihood, estimator.Econometric Theory10, 29–52.
  • [30] McCullagh, P. and Nelder, J. A., (1989).Generalized Linear Models, 2nd ed. Chapman & Hall, London.
  • [31] Meitz, M. and Saikkonen, P. (2008). Ergodicity, mixing, and existence of moments of a class of Markov models with application to GARCH and ACD, models.Econometric Theory24, 1291–1320.
  • [32] Meitz, M. and Saikkonen, P. (2011). Parameter estimation in nonlinear AR GARCH, models.Econometric Theory27, 1236–1278.
  • [33] Mikosch, T. and Straumann, D. (2006). Stable limits of martingale transforms with application to the estimation of GARCH, parameters.Ann. Statist.34, 493–522.
  • [34] Moysiadis, T. and Fokianos, K. (2014). On binary and categorical time series models with, feedback.Journal of Multivariate Analysis131, 209–228.
  • [35] Nelder, J. A. and Wedderburn, R. W. M. (1972). Generalized linear, models.Journal of the Royal Statistical Society, Series A135, 370– 384.
  • [36] Nelson, D. (1991). Conditional heteroskedasticity in asset returns: a new, approach.Econometrica59, 347–370.
  • [37] Pfanzagl, J. (1969). On the measurability and consistency of minimum contrast, estimates.Metrika14, 249–272.
  • [38] Russell, J. R. and Engle, R. F. (2005). A discrete-state continuous-time model of financial transactions prices and, times.Journal of Business and Economic Statistics23, 166–180.
  • [39] Rydberg, T. H. and Shephard, N. (2003). Dynamics of trade-by-trade price movements: decomposition and, models.Journal of Financial Econometrics1, 2–25.
  • [40] Streett, S. (2000). Some observation driven models for time series of counts. Ph.D. thesis, Colorado State University, Department of, Statistics.
  • [41] Teräsvirta, T. (1994). Specification, estimation, and evaluation of smooth transition autoregressive, models.Journal of the American Statistical Association89, 208–218.
  • [42] Teräsvirta, T., Tjøstheim, D., and Granger, C. W. J., (2010).Modelling Nonlinear Economic Time Series. Oxford University Press, Oxford.
  • [43] Wedderburn, R. W. M. (1974). Quasi–likelihood functions, generalized linear models and the Gaussian, method.Biometrika61, 439–447.
  • [44] West, M. and Harrison, J., (1989).Bayesian Forecasting and Dynamic Models. Springer.
  • [45] White, H. (1982). Maximum likelihood estimation of misspecified, models.Econometrica50, 1–25.
  • [46] Zeger, S. L. (1988). A regression model for time series of, counts.Biometrika75, 621.
  • [47] Zeger, S. L. and Liang, K.-Y. (1986). Longitudinal data analysis for discrete and continuous, outcomes.Biometrics42, 121–130.
  • [48] Zeger, S. L. and Qaqish, B. (1988). Markov regression models for time series: a quasi-likelihood, approach.Biometrics44, 1019–1031.