Asymptotic Variance Analysis of Subspace Identification Methods
2000 (English)In: IFAC Symp. on System Identification, 2000Conference paper (Refereed)
The class of subspace algorithms for system identication is an interesting complement to the maximum likelihood or prediction error methods, especially for multivariable systems. The statistical analysis of the subspace methods is dicult since the estimates depend on the data in a rather complicated manner. Previous results include proofs of generic consistency and asymptotic normality of the estimates. However, no explicit transparent expression for the covariance matrix of the limiting distribution has so far been reported because of the aforementioned diculties. The main objective of this paper is to provide a methodology that simplies the asymptotic analysis of subspace based estimation algorithms. The basic idea is illustrated by deriving the asymptotic covariance matrix corresponding to the estimates of the state-space matrices (or the transfer function estimate) of a quite general subspace algorithm.
Place, publisher, year, edition, pages
system identication, subspace algorithms, maximum likelihood, prediction error methods, generic consistency, asymptotic normality
IdentifiersURN: urn:nbn:se:kth:diva-82692OAI: oai:DiVA.org:kth-82692DiVA: diva2:498516
IFAC SYSID'2000: Symposium on System Identification, Santa Barbara, CA, USA, June 2000
NR 201408052012-02-122012-02-122012-02-12Bibliographically approved