Comparative Study of Sliding Window Multifractal Detrended Fluctuation Analysis and Multifractal Moving Average Algorithm

Abstract

Sliding window multifractal detrended fluctuation analysis (W-MFDFA) and multifractal moving average detrended method (MFDMA) are two effective methods to study multifractal characteristics of nonstationary time series. Taking the typical BMS signal model as an example, the selection of parameters, calculation accuracy and noise effects of the two algorithms are analyzed and compared. The results show that the calculation accuracy of MFDMA is better than that of W-MFDFA, but the latter is not sensitive to the changes of parameters, and has stronger anti-interference ability to noise and better stability. It can provide valuable reference for the research of actual data and the selection of internal parameters of the algorithm.