Model structure selection for multivariable systems by cross-validation methods

1 June 1988

journal article
research article
Published by Taylor & Francis in International Journal of Control

Vol. 47 (6) , 1737-1758
https://doi.org/10.1080/00207178808906133

Abstract

Using cross-validation ideas, two procedures are proposed for making a choice between different model structures used for (approximate) modelling of multivariable systems. The procedures are derived under fairly general conditions: the ‘true’ system does not need to be contained in the model set; model structures do not need to be nested and different criteria may be used for model estimation and validation. The proposed structure selection rules are shown to be invariant to parameter scaling. Under certain conditions (essentially requiring that the system belongs to the model set and that the maximum likelihood method is used for parameter estimation) they are shown to be asymptotically equivalent to the (generalized) Akaike structure selection criteria.

Keywords

This publication has 10 references indexed in Scilit:

Optimal experiment designs with respect to the intended model application
Automatica, 1986
Model-structure selection by cross-validation
International Journal of Control, 1986
On the choice of parameterization for identification
IEEE Transactions on Automatic Control, 1986
Order estimation by accumulated prediction errors
Journal of Applied Probability, 1986
Instrumental Variable Methods for System Identification
Published by Springer Nature ,1983
On-line structure selection for multivariable state-space models
Automatica, 1982
On non-singular information matrices and local identifiability
International Journal of Control, 1982
Convergence analysis of parametric identification methods
IEEE Transactions on Automatic Control, 1978
Kronecker products and matrix calculus in system theory
IEEE Transactions on Circuits and Systems, 1978
A new look at the statistical model identification
IEEE Transactions on Automatic Control, 1974