Title :
Smoothed multiple taper spectral analysis and adaptive implementation
Author :
Riedel, Kurt S. ; Sidorenko, Alexander
Author_Institution :
Courant Inst. of Math. Sci., New York, NY, USA
Abstract :
A hybrid estimator of the log-spectral density of a stationary time series is proposed. First, a multiple taper estimate is performed, followed by kernel smoothing the log-multitaper estimate. This procedure reduces the expected mean square error by ((π2)/4)0.8 over simply smoothing the log tapered periodogram. The optimal number of tapers is O(N8(15/)). A data adaptive implementation of a variable bandwidth kernel smoother is given
Keywords :
adaptive estimation; adaptive signal processing; optimisation; smoothing methods; spectral analysis; time series; adaptive implementation; data adaptive implementation; expected mean square error; hybrid estimator; kernel smoothing; log tapered periodogram; log-multitaper estimate; log-spectral density; optimal taper number; smoothed multiple taper spectral analysis; stationary time series; variable bandwidth kernel smoother; Bandwidth; Fourier transforms; Kernel; Matrix decomposition; Mean square error methods; Robustness; Smoothing methods; Spectral analysis; Statistics; Virtual colonoscopy;
Conference_Titel :
Time-Frequency and Time-Scale Analysis, 1994., Proceedings of the IEEE-SP International Symposium on
Conference_Location :
Philadelphia, PA
Print_ISBN :
0-7803-2127-8
DOI :
10.1109/TFSA.1994.467313
