Title :
On The Relation Between Weighted Frequency-Domain Maximum-Likelihood Power Spectral Estimation and the Prefiltered Covariance Extension Approach
Author :
Blomqvist, Anders ; Wahlberg, Bo
Author_Institution :
Kaupthing Bank Sverige AB, Stockholm
Abstract :
The aim of this correspondence is to study the connection between weighted frequency-domain maximum-likelihood power spectral estimation and the time-domain prefiltered covariance extension approach. Weighting and prefiltering are introduced to emphasize the model fit in a certain frequency range. The main result is that these two methods are very closely related for the case of autoregressive (AR) model estimation, which implies that both can be formulated as convex optimization problems. Examples illustrating the methods and the effect of prefiltering/weighting are provided
Keywords :
autoregressive processes; covariance analysis; filtering theory; frequency-domain analysis; maximum likelihood estimation; optimisation; time-domain analysis; autoregressive model estimation; convex optimization problems; maximum-likelihood power spectral estimation; prefiltered covariance extension approach; time-domain approach; weighted frequency-domain; Autoregressive processes; Filters; Frequency domain analysis; Frequency estimation; Maximum likelihood estimation; Optimization methods; Poles and zeros; Power system modeling; Spectral analysis; Time domain analysis; Autoregressive (AR) processes; covariance analysis; frequency-domain analysis; spectral analysis;
Journal_Title :
Signal Processing, IEEE Transactions on
DOI :
10.1109/TSP.2006.885780
