QML Estimation of Asymmetric Markov Switching GARCH(p, q) Processes

Abstract

In this paper, I propose a natural extension of time-invariant coefficients threshold GARCH (TGARCH) processes to time-varying one, in which the associated volatility switch between different regimes due to dependency of its coefficients on unobservable (latent) time homogeneous Markov chain with finite state space (MS-TGARCH). These models are showed to be capable to capture some phenomena observed for most financial time series, among others, the asymmetric patterns, leverage effects, dependency without correlation and tail heaviness. So, some theoretical probabilistic properties of such models are discussed, in particular, we establish firstly necessary and sufficient conditions ensuring the strict stationarity and ergodicity for solution process of MS-TGARCH. Secondary, we extend the standard results for the limit theory of the popular quasi-maximum likelihood estimator (QMLE) for estimating the unknown parameters involved in model and we examine thus the strong consistency of such estimates. The finite-sample properties of QMLE are illustrated by a Monte Carlo study. Our proposed model is applied to model the exchange rates of the Algerian Dinar against the single European currency (Euro).

Keywords

MS-TGARCH model / Strict stationarity / Strong consistency

References

[1] Alemohammad N, Rezakhah S, Alizadeh SH. Markov Switching asymmetric GARCH Model: stability and forecasting. Stat. Papers. 2018, 59 1-25

[2] Horvath LB, Kokoszka P. GARCH processes; structure and estimation. Bernoulli. 2003, 9 201-227

[3] Bibi A, Ghezal A. On the Markov-switching bilinear processes: stationarity, higher-order moments and $\beta -$mixing. Stoch. Int. J. Probab. Stoch. Process.. 2015, 87 6 919-945

[4] Bibi A, Ghezal A. Consistency of quasi-maximum likelihood estimator for Markov-switching bilinear time series models. Stat. Prob. Lett.. 2015, 100 192-202

[5] Bollerslev, T.: Glossary to ARCH (GARCH). Volatility and time series econometrics: essays in honour of Robert F. Angel. In: Bollerslev, T., Russell, J.R., Watson, M. (eds.). Oxford University Press, Oxford, UK (2009)

[6] Bougerol P, Picard N. Strict stationarity of generalized autoregressive processes. Ann. Probab.. 1992, 20 4 1714-1730

[7] Brandt A. The stochastic equation $Y_{N+1} =A_{N}Y_{N}+B_{N}$ with stationary coefficients. Adv. Appl. Probab.. 1986, 18 1 211-220

[8] Douc R, Moulines E, Stoffer D. Nonlinear Time Series Theory, Methods, and Applications with R Examples. 2014 Boca Raton: CRC Press

[9] Francq C, Zakoïan J-M. $\mathbb{L}^{2}-$Structures of standard and switching-regime GARCH models. Stoch. Proc. Appl.. 2005, 115 9 1557-1582

[10] Francq C, Zakoïan J-M. $QML$ estimation of a class of multivariate asymmetric GARCH models. Econom. Theory. 2012, 28 1 179-206

[11] Glosten LR, Jaganathan R, Runkle D. On the relation between the expected values and the volatility of the nominal excess return on stocks. J. Financ.. 1993, 48 5 1779-1801

[12] Haas, M., Liu, J.-C.: “Theory for a Multivariate Markov—switching GARCH Model with an Application to Stock Markets”. In: Annual Conference 2015 (Muenster): Economic Development—Theory and Policy 112855, Verein für Socialpolitik / German Economic Association (2015)

[13] Haas, M., Mittnik, S.: “Multivariate regime-switching GARCH with an application to international stock markets”. CFS Working Paper Series 2008/08, Center for Financial Studies (CFS) (2008)

[14] Hamadeh T, Zakoïan JM. Asymptotic properties of LS and QML estimators for a class of nonlinear GARCH processes. J. Stat. Plan. Inference. 2011, 141 1 488-507

[15] Hamdi, F., Souam, S.: Mixture periodic GARCH models: applications to exchange rate modeling. In: 5th International Conference on Modeling, Simulation and Applied Optimizatio (ICMSAO), Hammamet, Tunisie IEEE Xplore, 28–30 April 2013, pp. 1–6 (2013)

[16] Hamilton JD. A new approach to the economic analysis of nonstationary time series and the business cycle. Econometrica. 1989, 57 2 357-384

[17] Hwang SY, Basawa IV. Stationarity and moment structure for Box-Cox transformed threshold GARCH$(1,1)$ processes. Stat. Probab. Lett.. 2004, 68 3 209-220

[18] Hwang SY, Kim TY. Power transformation and threshold modeling for $ARCH$ innovations with applications to tests for ARCH structure. Stoch. Process. Appl.. 2004, 110 2 295-314

[19] Leroux BG. Maximum-likelihood estimation for hidden Markov models. Stoch. Process. Appl.. 1992, 40 127-143

[20] Liu Ji-Chun. Stationarity for a Markov-switching Box-Cox transformed threshold GARCH process. Stat. Prob. Lett.. 2007, 77 13 1428-1438

[21] Xie Y. Consistency of maximum likelihood estimators for the regimes witching GARCH model. Stat. J. Theor. Appl. Stat.. 2009, 43 2 153-165