DocumentCode :
417397
Title :
Closed form frequency domain expressions for best achievable accuracy of spectral density estimation
Author :
Ninness, Brett
Author_Institution :
Electr. Eng. & Comput. Sci., Univ. of Newcastle, Callaghan, NSW, Australia
Volume :
2
fYear :
2004
fDate :
17-21 May 2004
Abstract :
The paper addresses the issue of quantifying the frequency domain accuracy of ARMA spectral estimates as dictated by the Cramer-Rao lower bound (CRLB). Classical work in this area has led to expressions that are asymptotically exact as both data length and model order tend to infinity, although they are commonly used in finite model order and finite data length settings as approximations. More recent work has established quantifications which, for AR models, are exact for finite model order. By employing new analysis methods based on rational orthonormal parameterisations, together with the ideas of reproducing kernel Hilbert spaces, the paper develops quantifications that extend the previous work by being exact for finite model order in all of the AR, MA and ARMA system cases. These quantifications, via their explicit dependence on poles and zeros of the underlying spectral factor, reveal certain fundamental aspects of the accuracy achievable by spectral estimates of ARMA processes.
Keywords :
Hilbert spaces; autoregressive moving average processes; frequency-domain analysis; parameter estimation; poles and zeros; signal processing; spectral analysis; ARMA spectral estimates; CRLB; Cramer-Rao lower bound; closed form frequency domain expressions; finite data length; finite model order; kernel Hilbert spaces; orthonormal parameterisation; poles and zeros; spectral density estimation; Acoustic applications; Adaptive filters; Computer science; Econometrics; Frequency domain analysis; Frequency estimation; H infinity control; Hilbert space; Kernel; Poles and zeros;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Acoustics, Speech, and Signal Processing, 2004. Proceedings. (ICASSP '04). IEEE International Conference on
ISSN :
1520-6149
Print_ISBN :
0-7803-8484-9
Type :
conf
DOI :
10.1109/ICASSP.2004.1326300
Filename :
1326300
Link To Document :
بازگشت