Nonlinear filtering properties of detrended fluctuation analysis

Detrended fluctuation analysis (DFA) has been widely used for quantifying long-range correlation and fractal scaling behavior. In DFA, to avoid spurious detection of scaling behavior caused by a nonstationary trend embedded in the analyzed time series, a detrending procedure using piecewise least-squares fitting has been applied. However, it has been pointed out that the nonlinear filtering properties involved with detrending may induce instabilities in the scaling exponent estimation. To understand this issue, we investigate the adverse effects of the DFA detrending procedure on the statistical estimation. We show that the detrending procedure using piecewise least-squares fitting results in the nonuniformly weighted estimation of the root-mean-square deviation and that this property could induce an increase in the estimation error. In addition, for comparison purposes, we investigate the performance of a centered detrending moving average analysis with a linear detrending filter and sliding window DFA and show that these methods have better performance than the standard DFA.

[1]  W. Willinger,et al.  ESTIMATORS FOR LONG-RANGE DEPENDENCE: AN EMPIRICAL STUDY , 1995 .

[2]  Zbigniew R Struzik,et al.  Estimator of a non-Gaussian parameter in multiplicative log-normal models. , 2007, Physical review. E, Statistical, nonlinear, and soft matter physics.

[3]  Jose Alvarez-Ramirez,et al.  Detrending fluctuation analysis based on high-pass filtering , 2007 .

[4]  Ken Kiyono,et al.  Establishing a direct connection between detrended fluctuation analysis and Fourier analysis. , 2015, Physical review. E, Statistical, nonlinear, and soft matter physics.

[5]  Zbigniew R Struzik,et al.  Phase transition in a healthy human heart rate. , 2005, Physical review letters.

[6]  H. Stanley,et al.  Quantifying signals with power-law correlations: a comparative study of detrended fluctuation analysis and detrended moving average techniques. , 2004, Physical review. E, Statistical, nonlinear, and soft matter physics.

[7]  C. Peng,et al.  Mosaic organization of DNA nucleotides. , 1994, Physical review. E, Statistical physics, plasmas, fluids, and related interdisciplinary topics.

[8]  H. Stanley,et al.  Quantification of scaling exponents and crossover phenomena in nonstationary heartbeat time series. , 1995, Chaos.

[9]  Wei-Xing Zhou,et al.  Modified detrended fluctuation analysis based on empirical mode decomposition for the characterization of anti-persistent processes , 2009, 0907.3284.

[10]  H. Stanley,et al.  Multifractal Detrended Fluctuation Analysis of Nonstationary Time Series , 2002, physics/0202070.

[11]  H. Stanley,et al.  Effect of nonlinear filters on detrended fluctuation analysis. , 2004, Physical review. E, Statistical, nonlinear, and soft matter physics.

[12]  H E Stanley,et al.  Analysis of clusters formed by the moving average of a long-range correlated time series. , 2004, Physical review. E, Statistical, nonlinear, and soft matter physics.

[13]  H. Stanley,et al.  Detrended cross-correlation analysis: a new method for analyzing two nonstationary time series. , 2007, Physical review letters.

[14]  A. Carbone,et al.  Second-order moving average and scaling of stochastic time series , 2002 .

[15]  Ken Kiyono,et al.  Detrending moving average algorithm: Frequency response and scaling performances. , 2016, Physical review. E.

[16]  J. Álvarez-Ramírez,et al.  Detrending fluctuation analysis based on moving average filtering , 2005 .

[17]  Jari Saramäki,et al.  Exploring temporal networks with greedy walks , 2015, ArXiv.

[18]  Holger Kantz,et al.  The relationship between the detrendend fluctuation analysis and the autocorrelation function of a signal , 2015 .

[19]  S. Havlin,et al.  Comparison of detrending methods for fluctuation analysis , 2008, 0804.4081.

[20]  S. Havlin,et al.  Detecting long-range correlations with detrended fluctuation analysis , 2001, cond-mat/0102214.

[21]  Harvard Medical School,et al.  Effect of nonstationarities on detrended fluctuation analysis. , 2001, Physical review. E, Statistical, nonlinear, and soft matter physics.

[22]  Rangarajan,et al.  Integrated approach to the assessment of long range correlation in time series data , 2000, Physical review. E, Statistical physics, plasmas, fluids, and related interdisciplinary topics.

[23]  Ken Kiyono,et al.  Log-amplitude statistics of intermittent and non-Gaussian time series. , 2009, Physical review. E, Statistical, nonlinear, and soft matter physics.

[24]  H. Stanley,et al.  Effect of trends on detrended fluctuation analysis. , 2001, Physical review. E, Statistical, nonlinear, and soft matter physics.

[25]  Ken Kiyono,et al.  Fast algorithm for scaling analysis with higher-order detrending moving average method. , 2016, Physical review. E.

[26]  Thadeu Josino Pereira Penna,et al.  Fourier-detrended fluctuation analysis , 2005 .

[27]  D. Sornette,et al.  Comparing the performance of FA, DFA and DMA using different synthetic long-range correlated time series , 2012, Scientific Reports.

[28]  H. E. Hurst,et al.  Long-Term Storage Capacity of Reservoirs , 1951 .