Finite sample properties of system identification methods

IEEE Transactions on Automatic Control

Volumn 47, Issue 8, 2002, Pages 1329-1334

  Campi, M C ^a   Weyer, Erik ^b  

^a UNIVERSITY OF BRESCIA   (Italy)

^b UNIVERSITY OF MELBOURNE   (Australia)

Author keywords

Finite sample; Nonasymptotic theory; Prediction error methods; System identification

Indexed keywords

ASYMPTOTIC STABILITY; CONVERGENCE OF NUMERICAL METHODS; ERROR ANALYSIS; MATHEMATICAL MODELS; SPURIOUS SIGNAL NOISE;

NONASYMPTOTIC THEORY;

PARAMETER ESTIMATION;

EID: 0036687173     PISSN: 00189286     EISSN: None     Source Type: Journal    
DOI: 10.1109/TAC.2002.800750     Document Type: Article

References (20)

1. Nonparametric statistics for stochastic processes - Estimation and prediction
2. Learning dynamical systems in a stationary environment
3. ∞2 identification
4. Model quality evaluation in set membership identification
5. Nonparametric estimation of transfer functions: Rates of convergence and adaptation
6. Asymptotic properties of the least squares method for estimating transfer functions
7. Asymptotic properties of the least squares method for estimating transfer functions and disturbance spectra
8. ∞ identification of 'soft' uncertainty models
9. Minimum complexity regression estimation with weakly dependent observations
10. Memory-universal prediction of stationary random processes
11. Hard frequency-domain model error bounds from least-squares like identification techniques
12. Finite sample properties of system identification Of ARX models under mixing conditions
13. Non-asymptotic confidence ellipsoids for the least squares estimate
14. Finite sample properties of linear model identification