A Geometric Approach to Variance Analysis in System Identification
2011 (English)In: IEEE Transactions on Automatic Control, ISSN 0018-9286, E-ISSN 1558-2523, Vol. 56, no 5, 983-997 p.Article in journal (Refereed) Published
This paper addresses the problem of quantifying the model error ("variance-error") in estimates of dynamic systems. It is shown that, under very general conditions, the asymptotic ( in data length) covariance of an estimated system property ( represented by a smooth function of estimated system parameters) can be interpreted in terms of an orthogonal projection of a certain function, associated with the property of interest, onto a subspace determined by the model structure and experimental conditions. The presented geometric approach simplifies structural analysis of the model variance and this is illustrated by analyzing the influence of inputs and sensors on the model accuracy.
Place, publisher, year, edition, pages
2011. Vol. 56, no 5, 983-997 p.
Asymptotic covariance, model accuracy, stochastic systems, system identification
Research subject SRA - ICT
IdentifiersURN: urn:nbn:se:kth:diva-34220DOI: 10.1109/TAC.2010.2076213ISI: 000290536500002ScopusID: 2-s2.0-79955911807OAI: oai:DiVA.org:kth-34220DiVA: diva2:423463
FunderSwedish Research Council, 621-2007-6271Swedish Research Council, 621-2009-4017
QC 201106152011-06-152011-05-302012-01-19Bibliographically approved