Title :
Likelihood based uncertainty bounding in prediction error identification using ARX models: A simulation study
Author :
den Dekker, Arnold J. ; Bombois, Xavier ; Van den Hof, Paul M. J.
Author_Institution :
Delft Center for Syst. & Control, Delft Univ. of Technol., Delft, Netherlands
Abstract :
The purpose of this paper is to evaluate the reliability and finite sample properties of different likelihood based methods for constructing probabilistic parameter confidence regions in prediction error identification using ARX (Auto Regression with eXogenous inputs) models. The paper presents alternatives for the “classical” approach to constructing probabilistic confidence regions in prediction error identification.
Keywords :
autoregressive processes; maximum likelihood estimation; prediction theory; probability; reliability theory; uncertain systems; ARX models; auto regression with exogenous inputs models; finite sample properties; likelihood based methods; likelihood based uncertainty bounding; prediction error identification; probabilistic confidence regions; probabilistic parameter confidence regions; reliability; Data models; Maximum likelihood estimation; Predictive models; Transfer functions; Vectors; White noise;
Conference_Titel :
Control Conference (ECC), 2007 European
Conference_Location :
Kos
Print_ISBN :
978-3-9524173-8-6
