EcoSta 2022: Start Registration
View Submission - EcoSta2022
A0768
Title: Functional threshold autoregressive model Authors:  Kun Chen - Southwestern University of Finance and Economics (China) [presenting]
Chun Yip Yau - Chinese University of Hong Kong (Hong Kong)
Yuanbo Li - University of International Business and Economics (China)
Abstract: A functional threshold autoregressive model is proposed for flexible functional time series modeling. In particular, the behavior of a function at a given time point can be described by different autoregressive mechanisms according to different values of a threshold variable at a past time point. Sufficient conditions for strict stationarity and ergodicity of the functional threshold autoregressive process are investigated. A novel criterion-based method is developed to simultaneously conduct dimension reduction and estimation of thresholds, autoregressive orders, and model parameters. The consistency and asymptotic distributions of the estimators of both thresholds and underlying autoregressive models are established. Simulation studies and a real application of U.S. Treasury zero-coupon yield rates are provided to illustrate the effectiveness and usefulness of the proposed methodology.