EcoSta 2024: Start Registration
View Submission - EcoSta 2025
A1253
Title: On multiple-regime buffered auto-regressive processes Authors:  Wai-keung Li - The Education University of Hong Kong (Hong Kong) [presenting]
Zhoufan Zhu - Shanghai University of Finance and Economics (China)
Dong Li - Tsinghua University (China)
Ke Zhu - University of Hong Kong (Hong Kong)
Philip Yu - The Education University of Hong Kong (Hong Kong)
Abstract: The two-regime buffered autoregressive model was originally proposed about a decade ago as an extension of the threshold type time series models by considering a buffered zone for model switching. The model has achieved some successes in applications. In this paper an extension to time series with more than one buffer zone is considered. Simulations suggest the efficiency of the proposed modelling strategy and a real example illustrates the potential of the new model.