The permutation test as a non-parametric method for testing the statistical significance of power spectrum estimation in cyclostratigraphic research

Citation
E. Pardo-iguzquiza et Fj. Rodriguez-tovar, The permutation test as a non-parametric method for testing the statistical significance of power spectrum estimation in cyclostratigraphic research, EARTH PLAN, 181(1-2), 2000, pp. 175-189
Citations number
20
Categorie Soggetti
Earth Sciences
Journal title
EARTH AND PLANETARY SCIENCE LETTERS
ISSN journal
0012821X → ACNP
Volume
181
Issue
1-2
Year of publication
2000
Pages
175 - 189
Database
ISI
SICI code
0012-821X(20000830)181:1-2<175:TPTAAN>2.0.ZU;2-0
Abstract
A computer-intensive significance test for estimated power spectra of cycli c sedimentary successions is presented. This simple method requires no more than a few minutes in computer time for a PC-486, and does not require dis tributional assumptions. It is suitable for all the spectral analysis appro aches used in practice. Moreover, good performance is achieved with relativ ely short stratigraphical series. The method is similar to a permutation te st that has been successfully applied to other statistical problems. In the proposed application of the permutation test to the spectral analysis of t ime series, the data of a stratigraphic sequence are ordered at random (ran dom permutation) and the power spectrum is estimated by the given approach. The process is repeated many times (e.g. 1000 times) and thus it is possib le to assess the statistical significance of the power spectrum of the orig inal sequence for each frequency. Simulation results and the application to real data are shown in order to discuss the performance of the method. (C) 2000 Elsevier Science B.V. All rights reserved.