On correlations and fractal characteristics of time series

Simple item page
dc.creatorVitanov, Nikolay K.
dc.creatorSakai, kenschi
dc.creatorYankulova, Elka D.
dc.date2005-08-12
dc.date.accessioned2026-07-07T05:55:40Z
dc.date.available2026-07-07T05:55:40Z
dc.descriptionCorrelation analysis is convenient and frequently used tool for investigation of time series from complex systems. Recently new methods such as the multifractal detrended fluctuation analysis (MFDFA) and the wavelet transform modulus maximum method (WTMM) have been developed. By means of these methods (i) we can investigate long-range correlations in time series and (ii) we can calculate fractal spectra of these time series. But opposite to the classical tool for correlation analysis - the autocorrelation function, the newly developed tools are not applicable to all kinds of time series. The unappropriate application of MFDFA or WTMM leads to wrong results and conclusions. In this article we discuss the opportunities and risks connected to the application of the MFDFA method to time series from a random number generator and to experimentally measured time series (i) for accelerations of an agricultural tractor and (ii) for the heartbeat activity of {\sl Drosophila melanogaster}. Our main goal is to emphasize on what can be done and what can not be done by the MFDFA as tool for investigation of time series.
dc.description8 pages, 5 figures
dc.identifierhttps://arxiv.org/abs/physics/0508083
dc.identifierhttp://arxiv.org/abs/physics/0508083
dc.identifierJournal of Theoritical and Applied Mechanics, vol. 35. p.p. 73-90 (2005)
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/87323
dc.subjectData Analysis, Statistics and Probability
dc.subjectBiological Physics
dc.titleOn correlations and fractal characteristics of time series
dc.typetext

Files

Collections

arXiv