On the Markov-switching bilinear processes: stationarity, higher-order moments andβ-mixing

Abstract

This article investigates some probabilistic properties and statistical applications of general Markov-switching bilinear processes MS 2 BL ð Þthat offer remarkably rich dynamics and complex behaviour to model non-Gaussian data with structural changes. In these models, the parameters are allowed to depend on unobservable timehomogeneous and stationary Markov chain with finite state space. So, some basic issues concerning this class of models including necessary and sufficient conditions ensuring the existence of ergodic stationary (in some sense) solutions, existence of finite moments of any order and b-mixing are studied. As a consequence, we observe that the local stationarity of the underlying process is neither sufficient nor necessary to obtain the global stationarity. Also, the covariance functions of the process and its power are evaluated and it is shown that the second (respectively, higher)-order structure is similar to some linear processes, and hence admit ARMA representation. We establish also sufficient conditions for the MS-BL model to be b-mixing and geometrically ergodic. We then use these results to give sufficient conditions for b-mixing of a family of MS-GARCH ð1; 1Þ processes. A number of illustrative examples are given to clarify the theory and the variety of applications.

Spectral analysis of Markov switching GARCH models with statistical inference

“…Then we discuss spectral representations of MS GARCH models, and provide distributional theory for sample spectral density estimator. In a forthcoming paper, we shall apply the proposed methods to (bi)spectral analysis of Markov switching bilinear time series (see Bibi & Ghezal, 2015) as well as threshold‐asymmetric GARCH (Hwang & Baek, 2009) to provide statistical tests for linearity and Gaussianity of such general processes. Furthermore, given the importance of higher moments' properties, the proposed methods might be useful for statistical inference of other models (as, e.g., the stochastic volatility models from Andersen & Piterbarg, 2007).…”