作者: Petre Stoica , Tomas Sundin
DOI: 10.1007/BF01206681
关键词: Statistics 、 Estimator 、 Spectral density estimation 、 Mathematics 、 Smoothness (probability theory) 、 Stationary process 、 Spectral density 、 Applied mathematics 、 Efficiency 、 Nonparametric statistics 、 Piecewise
摘要: In this paper the Cramer-Rao bound (CRB) for a general nonparametric spectral estimation problem is derived under local smoothness condition (more exactly, spectrum assumed to be well approximated by piecewise constant function). Furthermore it shown that aforementioned Thomson (TM) and Danieli (DM) methods power density (PSD) can interpreted as approximations of maximum likelihood PSD estimator. Finally statistical efficiency TM DM estimators examined also compared CRB ARMA-based estimation. particular broadband signals, almost achieve performance therefore considered nearly optimal.