Proceedings of 1994 28th Asilomar Conference on Signals, Systems and Computers (1994)

Pacific Grove, CA, USA

Oct. 31, 1994 to Nov. 2, 1994

ISSN: 1058-6393

ISBN: 0-8186-6405-3

pp: 928-932

L.T. McWhorter , Dept. of Electr. & Comput. Eng., Colorado Univ., Boulder, CO, USA

L.L. Scharf , Dept. of Electr. & Comput. Eng., Colorado Univ., Boulder, CO, USA

ABSTRACT

Describes an algorithm for finding the exact maximum likelihood (ML) estimators for the parameters of an autoregressive time series. The authors demonstrate that the ML normal equations can be written as an interdependent set of cubic and quadratic equations in the AR polynomial coefficients. They present an algorithm, based on the properties of Sylvester resolvent matrices, that solves this set of non-linear equations for low-order problems.<>

INDEX TERMS

maximum likelihood estimation, time series, autoregressive processes, polynomials, matrix algebra, nonlinear equations

CITATION

L. McWhorter and L. Scharf, "Nonlinear maximum likelihood estimation of AR time series,"

*Proceedings of 1994 28th Asilomar Conference on Signals, Systems and Computers(ACSSC)*, Pacific Grove, CA, USA, 1995, pp. 928-932.

doi:10.1109/ACSSC.1994.471596

CITATIONS