Research Portal

Global convergence conditions in maximum likelihood estimation

Research output: Contribution to journal › Article › peer-review

Standard Standard

Global convergence conditions in maximum likelihood estimation. / Zou, Y.; Heath, W.P.
In: International Journal of Control, Vol. 85, No. 5, 05.2012, p. 475-490.

Research output: Contribution to journal › Article › peer-review

HarvardHarvard

Zou, Y & Heath, WP 2012, 'Global convergence conditions in maximum likelihood estimation', International Journal of Control, vol. 85, no. 5, pp. 475-490. https://doi.org/10.1080/00207179.2012.658085

APA

Zou, Y., & Heath, W. P. (2012). Global convergence conditions in maximum likelihood estimation. International Journal of Control, 85(5), 475-490. https://doi.org/10.1080/00207179.2012.658085

CBE

Zou Y, Heath WP. 2012. Global convergence conditions in maximum likelihood estimation. International Journal of Control. 85(5):475-490. https://doi.org/10.1080/00207179.2012.658085

MLA

Zou, Y. and W.P. Heath. "Global convergence conditions in maximum likelihood estimation". International Journal of Control. 2012, 85(5). 475-490. https://doi.org/10.1080/00207179.2012.658085

VancouverVancouver

Zou Y, Heath WP. Global convergence conditions in maximum likelihood estimation. International Journal of Control. 2012 May;85(5):475-490. Epub 2012 Feb 7. doi: 10.1080/00207179.2012.658085

Author

Zou, Y. ; Heath, W.P. / Global convergence conditions in maximum likelihood estimation. In: International Journal of Control. 2012 ; Vol. 85, No. 5. pp. 475-490.

RIS

TY - JOUR

T1 - Global convergence conditions in maximum likelihood estimation

AU - Zou, Y.

AU - Heath, W.P.

PY - 2012/5

Y1 - 2012/5

N2 - Maximum likelihood estimation has been widely applied in system identification because of consistency, its asymptotic efficiency and sufficiency. However, gradient-based optimisation of the likelihood function might end up in local convergence. In this article we derive various new non-local-minimum conditions in both open and closed-loop system when the noise distribution is a Gaussian process. Here we consider different model structures, in particular ARARMAX, BJ and OE models

AB - Maximum likelihood estimation has been widely applied in system identification because of consistency, its asymptotic efficiency and sufficiency. However, gradient-based optimisation of the likelihood function might end up in local convergence. In this article we derive various new non-local-minimum conditions in both open and closed-loop system when the noise distribution is a Gaussian process. Here we consider different model structures, in particular ARARMAX, BJ and OE models

U2 - 10.1080/00207179.2012.658085

DO - 10.1080/00207179.2012.658085

M3 - Erthygl

VL - 85

SP - 475

EP - 490

JO - International Journal of Control

JF - International Journal of Control

IS - 5

ER -