On the generation of high‐quality white noise series

J. Figwer and A. Niederlinski

Applied Stochastic Models and Data Analysis, 1992, vol. 8, issue 4, 311-326

Abstract: A new approach to the simulation of white‐noise time‐series is presented. The approach is based on the frequency‐domain property of white‐noise as having a flat power spectrum density (PSD). From such a PSD, a linear complex spectrum of random‐phase multisinusoidal series (MS) may be generated. Next, the fast Fourier transform is applied to this linear spectrum to generate a random‐phase multisinusoidal N‐sample series, simulating the white‐noise series. The properties of some MS series are discussed including a gaussian white noise multisinusoidal series. The idea is illustrated by a number of examples. They demonstrate that the spectral and correlation properties of such series are enhanced in comparison to the properties of the random phases used to generate them. They also demonstrate that the spectral and correlation properties of such series are better, especially for short series, in comparison with standard white noise generators.

Date: 1992
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://doi.org/10.1002/asm.3150080406

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:wly:apsmda:v:8:y:1992:i:4:p:311-326

Access Statistics for this article

More articles in Applied Stochastic Models and Data Analysis from John Wiley & Sons
Bibliographic data for series maintained by Wiley Content Delivery ().