Title :
AR(∞) estimation and nonparametric stochastic complexity
Author :
Gerencsér, László
Author_Institution :
Dept. of Electr. Eng., McGill Univ., Montreal, Que., Canada
Abstract :
Let H* be the transfer function of a linear stochastic system such that H* and its inverse are in H∞( D). Writing the system as an AR(∞) system, the best AR( k) approximation of the system is estimated using the method of least squares. Then the effect of undermodeling and parameter uncertainty (due to estimation) on prediction, and the optimal choice of k are investigated. The result is applied to the AR approximation of ARMA-systems
Keywords :
least squares approximations; parameter estimation; statistical analysis; stochastic processes; stochastic systems; transfer functions; ARMA-systems; least squares approximation; linear stochastic system; nonparametric stochastic complexity; parameter estimation; parameter uncertainty; transfer function; Control systems; Equations; H infinity control; Information theory; Polynomials; Stochastic processes; Stochastic systems; Transfer functions; Upper bound; Visualization;
Conference_Titel :
Decision and Control, 1990., Proceedings of the 29th IEEE Conference on
Conference_Location :
Honolulu, HI
DOI :
10.1109/CDC.1990.203704
