Estimating The Spectrum

Part of the Springer Texts in Statistics book series (STS)

Several alternative methods for constructing reasonable estimators of the spectral density have been proposed and investigated over the years. We will highlight just a few of them that have gained the most acceptance in light of present-day computing power. So-called nonparametric estimation of the spectral density (that is, smoothing of the sample spectral density) assumes very little about the shape of the “true” spectral density. Parametric estimation assumes that an autoregressive model—perhaps of high order—provides an adequate fit to the time series. The estimated spectral density is then based on the theoretical spectral density of the fitted AR model. Some other methods are touched on briefly.


Spectral Density Spectral Window Time Series Plot Fourier Frequency Dirichlet Kernel 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Springer Science+Business Media, LLC 2008

Personalised recommendations