Spectral Density Estimation Using Sharpened Periodograms

• Published in: IEEE transactions on signal processing Vol. 55; no. 9; pp. 4711 - 4716
• Main Authors: Fang Yao, Lee, T.C.M.
• Format: Journal Article
• Language: English
• Published: New York, NY IEEE 01-09-2007; Institute of Electrical and Electronics Engineers; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Applied sciences; Bias; Bias reduction; Data preprocessing; data sharpening; Density; Estimates; Exact sciences and technology; Information, signal and communications theory; Kernel; Mathematical analysis; periodogram smoothing; Probability; Reduction; sharpened periodograms; Signal and communications theory; Signal processing; Signal representation. Spectral analysis; Signal, noise; Smoothing; Smoothing methods; Spectra; spectral density estimation; Statistics; Telecommunications and information theory; unbiased risk estimation; Performance evaluation; Density estimation; Harmonic analysis; sharpened periodograms; spectral density estimation; data sharpening; Unbiased estimation; Spectrum analysis; periodogram smoothing; Bias reduction; Spectral density; Reduced order model; Signal analysis; unbiased risk estimation
• ISSN: 1053-587X; 1941-0476
• DOI: 10.1109/TSP.2007.896297

This correspondence introduces the use of sharpened periodograms for spectral density estimation. It is shown analytically that spectrum estimates obtained from smoothing the sharpened periodograms enjoy higher order bias reduction when compared with the ordinary smoothed periodogram estimates. The promising numerical performances of using sharpened periodograms for spectral density estimation are illustrated via numerical experiments.