Covariance Method (DSP Blockset)

Compute a parametric spectral estimate using the covariance method.

Library

Power Spectrum Estimation, in Estimation

Description

The Covariance Method block estimates the power spectral density (PSD) of the input using the covariance method. This method fits an autoregressive (AR) model to the signal by minimizing the forward prediction error in the least-squares sense. The spectrum is then computed from the FFT of the estimated AR model parameters.

The order of the all-pole model is specified by the Order parameter.

The input is a frame of consecutive time samples; a matrix input, u, is also treated as a single frame, u(:). The block's output is the estimate of the signal's power spectral density at N_fft equally spaced frequency points in the range [0,F_s), where N_fft is specified as a power of 2 by the FFT Size parameter and F_s is the signal's sample frequency. A value of -1 for FFT size instructs the block to use the input frame size as the FFT size. Otherwise, the block zero pads or truncates the input to N_fft before computing the FFT.

See the Burg Method block reference for a comparison of the Burg Method, Covariance Method, Modified Covariance Method, and Yule-Walker Method blocks.

Dialog Box

Input frame size: The number of samples in the input frame.
FFT size: The number of samples on which to perform the FFT, N_fft. If N_fft exceeds the frame size, the data is zero padded as needed.
Order: The order of the AR model.

References

Kay, S. M. Modern Spectral Estimation: Theory and Application. Englewood Cliffs, NJ: Prentice-Hall, 1988.

Marple, S. L., Jr., Digital Spectral Analysis with Applications. Englewood Cliffs, NJ: Prentice-Hall, 1987.