A New Approach to Model Structure Discrimination
- 1 January 1980
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Systems, Man, and Cybernetics
- Vol. 10 (2) , 78-84
- https://doi.org/10.1109/TSMC.1980.4308436
Abstract
In this paper a new characterization for the quality of stochastic, linear-in-parameters, difference equations models is given. This requires a good model to have accurate parameter estimates and uncorrelated residues. A criterion based on this characterization is derived and compared with other criteria which depend on minimizing the mean square of model residues.Keywords
This publication has 14 references indexed in Scilit:
- Estimating the Dimension of a ModelThe Annals of Statistics, 1978
- Prediction error estimators: Asymptotic normality and accuracyPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1976
- Selection of the order of an autoregressive model by Akaike's information criterionBiometrika, 1976
- A new look at the statistical model identificationIEEE Transactions on Automatic Control, 1974
- Uniqueness of the maximum likelihood estimates of the parameters of an ARMA modelIEEE Transactions on Automatic Control, 1974
- Optimal input signals for parameter estimation in dynamic systems--Survey and new resultsIEEE Transactions on Automatic Control, 1974
- Comparison of different methods for identification of industrial processesAutomatica, 1972
- Statistical predictor identificationAnnals of the Institute of Statistical Mathematics, 1970
- Fitting autoregressive models for predictionAnnals of the Institute of Statistical Mathematics, 1969
- A Mathematical Theory of CommunicationBell System Technical Journal, 1948