Stationarity and ergodic properties for some observation-driven models in random environments

DOI10.1214/23-AAP1944arXiv2007.07623OpenAlexW3043298365MaRDI QIDQ6180367FDOQ6180367

Authors: Paul Doukhan, Michael H. Neumann, Lionel Truquet 

Publication date: 19 January 2024

Published in: The Annals of Applied Probability (Search for Journal in Brave)

Abstract: The first motivation of this paper is to study stationarity and ergodic properties for a general class of time series models defined conditional on an exogenous covariates process. The dynamic of these models is given by an autoregressive latent process which forms a Markov chain in random environments. Contrarily to existing contributions in the field of Markov chains in random environments, the state space is not discrete and we do not use small set type assumptions or uniform contraction conditions for the random Markov kernels. Our assumptions are quite general and allows to deal with models that are not fully contractive, such as threshold autoregressive processes. Using a coupling approach, we study the existence of a limit, in Wasserstein metric, for the backward iterations of the chain. We also derive ergodic properties for the corresponding skew-product Markov chain. Our results are illustrated with many examples of autoregressive processes widely used in statistics or in econometrics, including GARCH type processes, count autoregressions and categorical time series.

Full work available at URL: https://arxiv.org/abs/2007.07623

Recommendations

• On categorical time series models with covariates
• Ergodicity of observation-driven time series models and consistency of the maximum likelihood estimator
• Stationarity and ergodicity of univariate generalized autoregressive score processes
• Ergodicity of a class of nonlinear time series models in random environment domain
• Study on a class of nonlinear time series models and ergodicity in random environment domain

zbMATH Keywords

time seriesMarkov chainsrandom environment

Mathematics Subject Classification ID

Time series, auto-correlation, regression, etc. in statistics (GARCH) (62M10) Discrete-time Markov processes on general state spaces (60J05) Processes in random environments (60K37)

Cites Work

• Analysis of Financial Time Series
• Ergodicity of observation-driven time series models and consistency of the maximum likelihood estimator
• Theory and inference for a class of nonlinear models with application to time series of counts
• Poisson autoregression
• Markov Regression Models for Time Series: A Quasi-Likelihood Approach
• Foundations of Modern Probability
• Self-excited threshold Poisson autoregression
• Qualitative threshold ARCH models
• Functional-Coefficient Autoregressive Models
• Nonlinear time series. Theory, methods and applications with R examples
• Strict stationarity of generalized autoregressive processes
• Stationarity of GARCH processes and of some nonnegative time series
• The stochastic equation Y_n+1=A_nY_n + B_n with stationary coefficients
• Absolute regularity and ergodicity of Poisson count processes
• Dynamic time series binary choice
• Threshold models in non-linear time series analysis
• Nonstationary Binary Choice
• Testing and Modeling Threshold Autoregressive Processes
• The General Equivalence of Granger and Sims Causality
• Threshold heteroskedastic models
• ERGODICITY, MIXING, AND EXISTENCE OF MOMENTS OF A CLASS OF MARKOV MODELS WITH APPLICATIONS TO GARCH AND ACD MODELS
• The ergodic theory of Markov chains in random environments
• Log-linear Poisson autoregression
• On binary and categorical time series models with feedback
• Stability and the Lyapounov exponent of threshold AR-ARCH models
• Perron-Frobenius theorem, large deviations, and random perturbations in random environments
• Coupling and perturbation techniques for categorical time series
• On categorical time series models with covariates
• On stability of nonlinear AR processes with Markov switching
• QML inference for volatility models with covariates
• Markov chains with stochastically stationary transition probabilities
• The Econometric Modelling of Financial Time Series
• Markov chains in random environments and random iterated function systems
• Stationarity and geometric ergodicity of a class of nonlinear ARCH models
• (Consistently) testing strict exogeneity against the alternative of predeterminedness in linear time-series models
• Stochastic models for time series
• Absolute regularity of semi-contractive GARCH-type processes
• Testing GARCH-X type models
• Iterations of dependent random maps and exogeneity in nonlinear dynamics

This page was built for publication: Stationarity and ergodic properties for some observation-driven models in random environments

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6180367)