On the asymptotic accuracy of pseudo-linear regression algorithms

The accuracy properties of a general pseudo-linear regression (PLR) method are examined. Both off-line and on-line algorithms are considered. Assuming the parameter estimates converge they will under weak conditions be asymptotically gaussian distributed. Expressions for the corresponding covariance...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:International journal of control Ročník 39; číslo 1; s. 115 - 126
Hlavní autoři: STOICA, P, SODERSTROM, T, AHLEN, A, SOLBRAND, G
Médium: Journal Article
Jazyk:angličtina
Vydáno: London Taylor & Francis Group 01.01.1984
Taylor & Francis
Témata:
Applied sciences
Computer science; control theory; systems
Control theory. Systems
Exact sciences and technology
Modelling and identification
Parameter estimation
System identification
Regression model
Algorithm
ISSN:0020-7179, 1366-5820
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:The accuracy properties of a general pseudo-linear regression (PLR) method are examined. Both off-line and on-line algorithms are considered. Assuming the parameter estimates converge they will under weak conditions be asymptotically gaussian distributed. Expressions for the corresponding covariance matrices are given. It is shown that the asymptotic covariance matrix of the off-line PLR algorithm is bounded from above by the matrix corresponding to the on-line PLR algorithm and from below by that corresponding to the prediction error method. Some simple numerical illustrations of the theoretical results are also included.
Bibliografie:ObjectType-Article-2
SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 23
ISSN:0020-7179
1366-5820
DOI:10.1080/00207178408933152