Unilateral 2D Markov-switching autoregressive model

DOI10.1504/IJMOR.2021.114208MaRDI QIDQ2664622zbMATH OpenFDO

Authors Houria Djafri, Soumia Kharfouchi

Publication date 17 November 2021

Published in International Journal of Mathematics in Operational Research (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1504/IJMOR.2021.114208

zbMATH Keywords

Markov random field (MRF)Markov-switching autoregressiveregional volatility

Mathematics Subject Classification ID

Time series, auto-correlation, regression, etc. in statistics (GARCH) (62M10) Inference from spatial processes (62M30) Random fields; image analysis (62M40)

Review text

Summary: For nonlinear two-dimensional spatial data, a 2D Markov-switching unilateral autoregressive model is defined. Strict stationarity is studied and parameter estimation via the variational expectation maximisation (VEM) algorithm is performed. First, a 2D Markov random field (MRF) is constructed for which an imposed causality allows to establish an analogy between this 2D MRF and the Markov chain representation. Based on the proposed 2D MRF, the 2D MS-AR model is defined under some necessary assumptions and useful notations. Finally, parameter estimation of the model is discussed paving the way to broad exploitation perspectives of the proposed 2D MS-AR processes to efficiently model several phenomena exhibiting a structural break in spatial data.

Recommendations

• Properties of the spatial unilateral first-order ARMA model
• Estimation of parameters of a two-dimensional spatial autoregressive model with regression
• The stationary regions for the parameter space of unilateral second-order spatial AR model
• A transitional Markov switching autoregressive model
• Stationnarité des modèles ARMA à changement de régime markovien

This page was built for publication: Unilateral 2D Markov-switching autoregressive model

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2664622)