Frequency domain system identification using nonparametric noise models estimated from a small number of data sets

Research output: Contribution to journalArticle

Abstract

In this paper a consistent frequency domain estimator is proposed in
the errors-in-variables framework. A nonparametric noise model (the
sample covariance matrix) directly obtained from a small number of
repeated measurements is used. The loss in efficiency due to use of the
sample covariance matrix instead of the exact covariance matrix is
quantified.
Original languageEnglish
JournalAutomatica
Publication statusPublished - 1997

Bibliographical note

Automatica, vol. 33, no. 6, pp. 1073-1086, 1997

Fingerprint Dive into the research topics of 'Frequency domain system identification using nonparametric noise models estimated from a small number of data sets'. Together they form a unique fingerprint.

Cite this