Title :
A Kalman filter based approach for estimating nonstationary VAR models via pole tracking
Author :
Elling, Michael ; Sherman, Peter
Author_Institution :
Iowa State Univ., Ames, IA, USA
Abstract :
A time-varying vector autoregressive (VAR) model is used for the modeling of time series with changing spectral content. Our approach focuses on the model´s time-varying poles. We show the relationship between the deviations in these poles and deviations in the VAR coefficients, which leads to a reparameterization of the model. The performance characteristics of the model are investigated by using simulation
Keywords :
Kalman filters; autoregressive processes; parameter estimation; poles and zeros; spectral analysis; time series; time-varying systems; Kalman filter based approach; nonstationary VAR models; performance characteristics; pole tracking; reparameterization; spectral content; time series; time-varying poles; time-varying vector autoregressive model; Covariance matrix; Earthquakes; Filtering; Kalman filters; Parameter estimation; Reactive power; State estimation; Time varying systems; White noise; Yttrium;
Conference_Titel :
Acoustics, Speech, and Signal Processing, 2000. ICASSP '00. Proceedings. 2000 IEEE International Conference on
Conference_Location :
Istanbul
Print_ISBN :
0-7803-6293-4
DOI :
10.1109/ICASSP.2000.859052
