Journal:International journal of control
Key Words:MLE; optimisation; global/local convergence; consistency; asymptotic efficiency and sufficiency; non-local-minimum conditions
Abstract: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.
Co-author:William Heath
First Author:Yiqun Zou*
Indexed by:Journal paper
Volume:85
Issue:5
Page Number:475–490
Translation or Not:no
Included Journals:SCI
Links to published journals:https://www.tandfonline.com/doi/abs/10.1080/00207179.2012.658085