Estimating the dimension of a linear system
- 1 December 1981
- journal article
- Published by Elsevier BV in Journal of Multivariate Analysis
- Vol. 11 (4), 459-473
- https://doi.org/10.1016/0047-259x(81)90089-0
Abstract
The problem considered is that of estimating the integer or integers that prescribe the dimension of a linear system. These could be the Kronecker indices. Though attention is concentrated on the order or McMillan degree, which specifies the dimension of a minimal state vector, the same results are available for other cases. A fairly complete theorem is proved relating to conditions under which strong or weak convergence will hold for an estimate of the McMillan degree when the estimation is based on minimisation of a criterion of the form log det(Ω̌n) + nC(T)/T, where Ω̌n, is the estimate of the prediction error covariance matrix and the McMillan degree is assumed to be n. The conditions relate to the prescribed sequence C(T)Keywords
This publication has 11 references indexed in Scilit:
- Some properties of the parameterization of ARMA systems with unknown orderJournal of Multivariate Analysis, 1981
- Estimation of vector ARMAX modelsJournal of Multivariate Analysis, 1980
- The Estimation of the Order of an ARMA ProcessThe Annals of Statistics, 1980
- Consistent estimation of system orderIEEE Transactions on Automatic Control, 1979
- Vector linear time series models: corrections and extensionsAdvances in Applied Probability, 1978
- Vector linear time series modelsAdvances in Applied Probability, 1976
- Canonical forms for the identification of multivariable linear systemsIEEE Transactions on Automatic Control, 1974
- Asymptotic Independence of the Numbers of High and Low Level Crossings of Stationary Gaussian ProcessesThe Annals of Mathematical Statistics, 1971
- Fitting autoregressive models for predictionAnnals of the Institute of Statistical Mathematics, 1969
- On the Law of the Iterated LogarithmAmerican Journal of Mathematics, 1941