Title :
First-order tracking properties of weighted least squares estimators
Author :
Niedzwiecki, Maciej
Author_Institution :
Dept. of Syst. Eng., Australian Nat. Univ., Canberra, ACT
fDate :
1/1/1988 12:00:00 AM
Abstract :
The first-order tracking properties (evolution of the mean tracking error) of weighted-least-squares (WLS) estimators applied to nonstationary system identification are investigated. The expected path of the parameter estimates is evaluated. The concept of the impulse response associated with the WLS estimator is introduced
Keywords :
difference equations; least squares approximations; parameter estimation; stochastic systems; time-varying systems; difference equations; first-order tracking properties; identification; impulse response; least squares approximations; nonstationary system; parameter estimation; stochastic systems; time varying systems; weighted least squares estimators; Artificial intelligence; Difference equations; History; Least squares approximation; Nonlinear filters; Parameter estimation; Stochastic systems; System identification; Vectors; Yield estimation;
Journal_Title :
Automatic Control, IEEE Transactions on
