论文信息 - A new order selection method for auto-regressive processes

A new order selection method for auto-regressive processes

An approximate formula for the residual variance of autoregressive modeling with the least-squares-forward (LSF) method is derived. By using this formula the statistical behavior of the residual variance is determined approximately. Based on this formula, a new sequential testing algorithm for order selection of auto-regressive processes is proposed. The performance of the algorithm is demonstrated by computer simulations.

Mahmood Karimi | M. H. Bastani

[1] B. G. Quinn,et al. The determination of the order of an autoregression , 1979 .

[2] J. Rissanen,et al. Modeling By Shortest Data Description* , 1978, Autom..

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

[4] E. Hannan,et al. The determination of optimum structures for the state space representation of multivariate stochastic processes , 1982 .

[5] Konstantinos Konstantinides. Threshold bounds in SVD and a new iterative algorithm for order selection in AR models , 1991, IEEE Trans. Signal Process..

[6] S.M. Kay,et al. Spectrum analysis—A modern perspective , 1981, Proceedings of the IEEE.

[7] G. Schwarz. Estimating the Dimension of a Model , 1978 .