DocumentCode
700841
Title
Study of conditional ML estimators in time and frequency domain system identification
Author
Schoukens, J. ; Pintelon, R. ; Rolain, Y.
Author_Institution
Dept. ELEC, Vrije Univ. Brussel, Brussels, Belgium
fYear
1997
fDate
1-7 July 1997
Firstpage
2442
Lastpage
2447
Abstract
This paper studies the impact of replacing the full covariance matrix by its main diagonal in maximum likelihood estimation (MLE) of linear dynamic systems in the time or frequency domain. First the source of the nondiagonal entries is studied, next the impact of neglecting these terms on the efficiency of the estimators is analyzed. Finally the equivalence between the time and frequency domain formulation is shown.
Keywords
frequency-domain analysis; linear systems; maximum likelihood estimation; time-domain analysis; time-varying systems; MLE; conditional ML estimators; estimator efficiency; frequency domain system identification; linear dynamic systems; maximum likelihood estimation; nondiagonal entries; time domain system identification; Cost function; Covariance matrices; Discrete Fourier transforms; Frequency-domain analysis; Maximum likelihood estimation; Noise; Time-domain analysis; estimation; linear identification; stochastics;
fLanguage
English
Publisher
ieee
Conference_Titel
Control Conference (ECC), 1997 European
Conference_Location
Brussels
Print_ISBN
978-3-9524269-0-6
Type
conf
Filename
7082472
Link To Document