Physics – Data Analysis – Statistics and Probability
Scientific paper
2005-08-12
Journal of Theoritical and Applied Mechanics, vol. 35. p.p. 73-90 (2005)
Physics
Data Analysis, Statistics and Probability
8 pages, 5 figures
Scientific paper
Correlation 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.
Sakai kenschi
Vitanov Nikolay K.
Yankulova Elka D.
No associations
LandOfFree
On correlations and fractal characteristics of time series does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with On correlations and fractal characteristics of time series, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and On correlations and fractal characteristics of time series will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-38498