Robust Parametric Transfer Function Estimation Using Complex Logarithmic Frequency Response Data

Research output: Contribution to journalArticle

49 Citations (Scopus)

Abstract

The statistical properties of a logarithmic least-squares
frequency-domain estimator are analyzed in an ''error in-variables''
framework, It is shown that, contrary to most frequency-domain
estimators, the logarithmic least-squares estimator remains
''practically'' consistent when the variances of the frequency-domain
data are not a priori known. If available, the variance at each
spectral line of the logarithmic frequency response data can be used to
weight the logarithmic least-squares estimator, resulting in parameter
estimates with a smaller variability, An estimate of these variances
can be derived from the residual errors at the excited spectral lines,
Besides its robustness to lack of prior noise information, it is
demonstrated that the logarithmic estimator behaves remarkably web in
the presence of outliers.
Original languageEnglish
JournalIEEE Transactions on Automatic Control
Publication statusPublished - 1 Jul 1995

Bibliographical note

IEEE Transactions on Automatic Control, Vol. 40, No. 7, July 1995, pp. 1180–1190

Fingerprint

Dive into the research topics of 'Robust Parametric Transfer Function Estimation Using Complex Logarithmic Frequency Response Data'. Together they form a unique fingerprint.

Cite this