liu.seSearch for publications in DiVA
Change search
ReferencesLink to record
Permanent link

Direct link
Regressor Selection with the Analysis of Variance Method
Linköping University, Department of Electrical Engineering, Automatic Control. Linköping University, The Institute of Technology.
Linköping University, Department of Electrical Engineering, Automatic Control. Linköping University, The Institute of Technology.
2004 (English)Report (Other academic)
Abstract [en]

Identication of nonlinear dynamical models of a black box nature involves both structure decisions, i.e., which regressors to use, the selection of a regressor function, and the estimation of the parameters involved. The typical approach in system identication seems to be to mix all these steps, which for example means that the selection of regressors is based on the ts that is achieved for dierent choices. Alternatively one could then interpret the regressor selection as based on hypothesis tests (F-tests) at a certain condence level that depends on the data. It would in many cases be desirable to decide which regressors to use independently of the other steps.

In this paper we investigate what the well known method of analysis of variance (ANOVA) can oer for this problem. System identication applications violate many of the ideal conditions for which ANOVA was designed and we study how the method performs under such non-ideal conditions.

ANOVA is much faster than a typical parametric estimation method, using e.g. neural networks. It is actually also more reliable, in our tests, in picking the correct structure even under non-ideal conditions. One reason for this may be that ANOVA requires the data set to be balanced, that is regressor value combinations in test/validation data that are very common or unusual are adjusted in order to play more equal roles when deciding their in uence on the t. Just applying tests of t for the recorded data may give improper weight to very common regressor value combinations.

Place, publisher, year, edition, pages
Linköping: Linköping University Electronic Press, 2004. , 10 p.
LiTH-ISY-R, ISSN 1400-3902 ; 2626
Keyword [en]
Time delay estimation, Time lag, Identification, Non-linear models, Analysis of variance
National Category
Control Engineering
URN: urn:nbn:se:liu:diva-55995ISRN: LiTH-ISY-R-2626OAI: diva2:316740
Available from: 2010-04-30 Created: 2010-04-30 Last updated: 2014-09-04Bibliographically approved

Open Access in DiVA

fulltext(207 kB)61 downloads
File information
File name FULLTEXT01.pdfFile size 207 kBChecksum SHA-512
Type fulltextMimetype application/pdf

Search in DiVA

By author/editor
Lind, IngelaLjung, Lennart
By organisation
Automatic ControlThe Institute of Technology
Control Engineering

Search outside of DiVA

GoogleGoogle Scholar
Total: 61 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Total: 43 hits
ReferencesLink to record
Permanent link

Direct link