A theoretical analysis of recursive identification methods
(1978) In Automatica 14(3). p.231-244- Abstract
- In this paper five different recursive identification methods will be analyzed and compared, namely recursive versions of the least squares method, the instrumental variable method, the generalized least squares method, the extended least squares method and the maximum likelihood method. They are shown to be similar in structure and need of computer storage and time. Making use of recently developed theory for asymptotic analysis of recursive stochastic algorithms, these methods are examined from a theoretical viewpoint. Possible convergence points and their global and local convergence properties are studied. The theoretical analysis is illustrated and supplemented by simulations.
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/0c6b86f2-43bf-4f03-b05d-5feb1cd34f56
- author
- Söderström, Torsten ; Ljung, Lennart and Gustavsson, Ivar
- organization
- publishing date
- 1978
- type
- Contribution to journal
- publication status
- published
- subject
- in
- Automatica
- volume
- 14
- issue
- 3
- pages
- 231 - 244
- publisher
- Elsevier
- external identifiers
-
- scopus:0017961729
- ISSN
- 0005-1098
- DOI
- 10.1016/0005-1098(78)90088-2
- language
- English
- LU publication?
- no
- id
- 0c6b86f2-43bf-4f03-b05d-5feb1cd34f56
- date added to LUP
- 2018-12-10 10:32:19
- date last changed
- 2025-04-04 14:37:43
@article{0c6b86f2-43bf-4f03-b05d-5feb1cd34f56,
abstract = {{In this paper five different recursive identification methods will be analyzed and compared, namely recursive versions of the least squares method, the instrumental variable method, the generalized least squares method, the extended least squares method and the maximum likelihood method. They are shown to be similar in structure and need of computer storage and time. Making use of recently developed theory for asymptotic analysis of recursive stochastic algorithms, these methods are examined from a theoretical viewpoint. Possible convergence points and their global and local convergence properties are studied. The theoretical analysis is illustrated and supplemented by simulations.}},
author = {{Söderström, Torsten and Ljung, Lennart and Gustavsson, Ivar}},
issn = {{0005-1098}},
language = {{eng}},
number = {{3}},
pages = {{231--244}},
publisher = {{Elsevier}},
series = {{Automatica}},
title = {{A theoretical analysis of recursive identification methods}},
url = {{http://dx.doi.org/10.1016/0005-1098(78)90088-2}},
doi = {{10.1016/0005-1098(78)90088-2}},
volume = {{14}},
year = {{1978}},
}