Home > Research > Publications & Outputs > Refined instrumental variable estimation

Research

Associated organisational unit

Links

Text available via DOI:

Keywords

View graph of relations

Refined instrumental variable estimation: maximum likelihood optimization of a unified Box-Jenkins model

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Published

Standard

Refined instrumental variable estimation: maximum likelihood optimization of a unified Box-Jenkins model. / Young, Peter.
In: Automatica, Vol. 52, 02.2015, p. 35-46.

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Harvard

Young, P 2015, 'Refined instrumental variable estimation: maximum likelihood optimization of a unified Box-Jenkins model', Automatica, vol. 52, pp. 35-46. https://doi.org/10.1016/j.automatica.2014.10.126

APA

Young, P. (2015). Refined instrumental variable estimation: maximum likelihood optimization of a unified Box-Jenkins model. Automatica, 52, 35-46. https://doi.org/10.1016/j.automatica.2014.10.126

Vancouver

Young P. Refined instrumental variable estimation: maximum likelihood optimization of a unified Box-Jenkins model. Automatica. 2015 Feb;52:35-46. doi: 10.1016/j.automatica.2014.10.126

Author

Young, Peter. / Refined instrumental variable estimation : maximum likelihood optimization of a unified Box-Jenkins model. In: Automatica. 2015 ; Vol. 52. pp. 35-46.

Bibtex

@article{69d517cd574d43909ab5f362bc6190a8,
title = "Refined instrumental variable estimation: maximum likelihood optimization of a unified Box-Jenkins model",
abstract = "For many years, various methods for the identification and estimation of parameters in linear, discrete-time transfer functions have been available and implemented in widely available Toolboxes for Matlab. This paper considers a unified Refined Instrumental Variable (RIV) approach to the estimation of discrete and continuous-time transfer functions characterized by a unified operator that can be interpreted in terms of backward shift, derivative or delta operators. The estimation is based on the formulation of a pseudo-linear regression relationship involving optimal prefilters that is derived from an appropriately unified Box-Jenkins transfer function model. The paper shows that, contrary to apparently widely held beliefs, the iterative RIV algorithm provides a reliable solution to the maximum likelihood optimization equations for this class of Box-Jenkins transfer function models and so its en bloc or recursive parameter estimates are optimal in maximum likelihood, prediction error minimization and instrumental variable terms.",
keywords = "System identification, Box–Jenkins model, Maximum likelihood, Optimal instrumental variable, En-bloc estimation, Recursive estimation",
author = "Peter Young",
year = "2015",
month = feb,
doi = "10.1016/j.automatica.2014.10.126",
language = "English",
volume = "52",
pages = "35--46",
journal = "Automatica",
issn = "0005-1098",
publisher = "Elsevier Limited",

}

RIS

TY - JOUR

T1 - Refined instrumental variable estimation

T2 - maximum likelihood optimization of a unified Box-Jenkins model

AU - Young, Peter

PY - 2015/2

Y1 - 2015/2

N2 - For many years, various methods for the identification and estimation of parameters in linear, discrete-time transfer functions have been available and implemented in widely available Toolboxes for Matlab. This paper considers a unified Refined Instrumental Variable (RIV) approach to the estimation of discrete and continuous-time transfer functions characterized by a unified operator that can be interpreted in terms of backward shift, derivative or delta operators. The estimation is based on the formulation of a pseudo-linear regression relationship involving optimal prefilters that is derived from an appropriately unified Box-Jenkins transfer function model. The paper shows that, contrary to apparently widely held beliefs, the iterative RIV algorithm provides a reliable solution to the maximum likelihood optimization equations for this class of Box-Jenkins transfer function models and so its en bloc or recursive parameter estimates are optimal in maximum likelihood, prediction error minimization and instrumental variable terms.

AB - For many years, various methods for the identification and estimation of parameters in linear, discrete-time transfer functions have been available and implemented in widely available Toolboxes for Matlab. This paper considers a unified Refined Instrumental Variable (RIV) approach to the estimation of discrete and continuous-time transfer functions characterized by a unified operator that can be interpreted in terms of backward shift, derivative or delta operators. The estimation is based on the formulation of a pseudo-linear regression relationship involving optimal prefilters that is derived from an appropriately unified Box-Jenkins transfer function model. The paper shows that, contrary to apparently widely held beliefs, the iterative RIV algorithm provides a reliable solution to the maximum likelihood optimization equations for this class of Box-Jenkins transfer function models and so its en bloc or recursive parameter estimates are optimal in maximum likelihood, prediction error minimization and instrumental variable terms.

KW - System identification

KW - Box–Jenkins model

KW - Maximum likelihood

KW - Optimal instrumental variable

KW - En-bloc estimation

KW - Recursive estimation

U2 - 10.1016/j.automatica.2014.10.126

DO - 10.1016/j.automatica.2014.10.126

M3 - Journal article

VL - 52

SP - 35

EP - 46

JO - Automatica

JF - Automatica

SN - 0005-1098

ER -