论文信息 - A new order estimation technique for time series modeling

A new order estimation technique for time series modeling

A new approach to estimating the order of the autoregressive moving average model is proposed, which is based on the approximate stochastic realization introduced in Davis and Fotopoulos (1991). The present approach is attractive because overparameterization-a very common problem in order determination-is avoided successfully. Simulation results are included to illustrate the effectiveness of the proposed order estimation approach.

Wei Xing Zheng | Mark H. A. Davis | W. Zheng

[1] Mark H. A. Davis,et al. Strong Consistency of the PLS Criterion for Order Determination of Autoregressive Processes , 1989 .

[2] J. Fuchs,et al. ARMA-Order estimation via matrix perturbation theory , 1986, 1986 25th IEEE Conference on Decision and Control.

[3] W. Gragg,et al. On the partial realization problem , 1983 .

[4] E. Hannan,et al. The statistical theory of linear systems , 1989 .

[5] J. Cadzow,et al. Spectral estimation: An overdetermined rational model equation approach , 1982, Proceedings of the IEEE.

[6] P. Caines. Linear Stochastic Systems , 1988 .

[7] Janusz S. Kowalik,et al. Iterative methods for nonlinear optimization problems , 1972 .

[8] E. Hannan,et al. Autocorrelation, Autoregression and Autoregressive Approximation , 1982 .

[9] Mark H. A. Davis,et al. On the approximate stochastic realisation problem , 1991, [1991] Proceedings of the 30th IEEE Conference on Decision and Control.

[10] H. Akaike. A new look at the statistical model identification , 1974 .

[11] J. C. Chow. On estimating the orders of an autoregressive moving-average process with uncertain observations , 1972 .

[12] R. Kashyap. Inconsistency of the AIC rule for estimating the order of autoregressive models , 1980 .