Evolutionary Spectra Based on the Multitaper Method with Application To Stationarity Test

In this work, we propose a new inference procedure for understanding non-stationary processes, under the framework of evolutionary spectra developed by Priestley. Among various frameworks of modeling non-stationary processes, the distinguishing feature of the evolutionary spectra is its focus on the physical meaning of frequency. The classical estimate of the evolutionary spectral density is based on a double-window technique consisting of a short-Fourier transform and a smoothing. However, smoothing is known to suffer from the so-called bias leakage problem. By incorporating Thomson's multitaper method that was originally designed for stationary processes, we propose an improved estimate of the evolutionary spectral density, and analyze its bias/variance/resolution tradeoff. As an application of the new estimate, we further propose a non-parametric rank-based stationarity test, and provide various experimental studies.

[1]  José Luis Romero,et al.  MSE Estimates for Multitaper Spectral Estimation and Off-Grid Compressive Sensing , 2017, IEEE Transactions on Information Theory.

[2]  R. Dahlhaus.  Fitting time series models to nonstationary processes , 1997 .

[3]  S. Mallat,et al.  Adaptive covariance estimation of locally stationary processes , 1998 .

[4]  Donald B. Percival,et al.  The variance of multitaper spectrum estimates for real Gaussian processes , 1994, IEEE Trans. Signal Process..

[5]  R. Dahlhaus.  On the Kullback-Leibler information divergence of locally stationary processes , 1996 .

[6]  Hualou Liang,et al.  Short-window spectral analysis of cortical event-related potentials by adaptive multivariate autoregressive modeling: data preprocessing, model validation, and variability assessment , 2000, Biological Cybernetics.

[7]  E. S. Pearson.  THE ANALYSIS OF VARIANCE IN CASES OF NON-NORMAL VARIATION , 1931 .

[8]  D. Slepian.  Prolate spheroidal wave functions, fourier analysis, and uncertainty — V: the discrete case , 1978, The Bell System Technical Journal.

[9]  L. Isserlis,et al.  ON CERTAIN PROBABLE ERRORS AND CORRELATION COEFFICIENTS OF MULTIPLE FREQUENCY DISTRIBUTIONS WITH SKEW REGRESSION , 1916 .

[10]  G. Nason.  A test for second‐order stationarity and approximate confidence intervals for localized autocovariances for locally stationary time series , 2013 .

[11]  Heidi Cullen,et al.  A Pervasive Millennial-Scale Cycle in North Atlantic Holocene and Glacial Climates , 1997 .

[12]  P. A. Blight.  The Analysis of Time Series: An Introduction , 1991 .

[13]  Donald B. Percival,et al.  Spectrum estimation by wavelet thresholding of multitaper estimators , 1998, IEEE Trans. Signal Process..

[14]  Patrick Flandrin,et al.  Wigner-Ville spectral analysis of nonstationary processes , 1985, IEEE Trans. Acoust. Speech Signal Process..

[15]  J. Lakey,et al.  Duration and Bandwidth Limiting: Prolate Functions, Sampling, and Applications , 2011 .

[16]  J. Raz,et al.  Automatic Statistical Analysis of Bivariate Nonstationary Time Series , 2001 .

[17]  D. Kendall,et al.  The Statistical Analysis of Variance‐Heterogeneity and the Logarithmic Transformation , 1946 .

[18]  M. Friedman.  The Use of Ranks to Avoid the Assumption of Normality Implicit in the Analysis of Variance , 1937 .

[19]  G. Glass,et al.  Consequences of Failure to Meet Assumptions Underlying the Fixed Effects Analyses of Variance and Covariance , 1972 .

[20]  M. B. Priestley,et al.  A Test for Non‐Stationarity of Time‐Series , 1969 .

[21]  R. Dahlhaus,et al.  On the Optimal Segment Length for Parameter Estimates for Locally Stationary Time Series , 1998 .

[22]  R. Dahlhaus,et al.  Asymptotic statistical inference for nonstationary processes with evolutionary spectra , 1996 .

[23]  M. Priestley.  Evolutionary Spectra and Non‐Stationary Processes , 1965 .

[24]  Simon Haykin,et al.  Cognitive radio: brain-empowered wireless communications , 2005, IEEE Journal on Selected Areas in Communications.

[25]  D. Slepian,et al.  Prolate spheroidal wave functions, fourier analysis and uncertainty — II , 1961 .

[26]  Donald B. Percival,et al.  Spectral Analysis for Physical Applications , 1993 .

[27]  Andrew T. Walden,et al.  Statistical Properties for Coherence Estimators From Evolutionary Spectra , 2012, IEEE Transactions on Signal Processing.

[28]  Patrick Flandrin,et al.  Time-Frequency/Time-Scale Analysis , 1998 .

[29]  Richard A. Davis,et al.  Time Series: Theory and Methods , 2013 .

[30]  C. Page.  Instantaneous Power Spectra , 1952 .

[31]  D. Thomson,et al.  Spectrum estimation and harmonic analysis , 1982, Proceedings of the IEEE.

[32]  Arnaud Delorme,et al.  EEGLAB: an open source toolbox for analysis of single-trial EEG dynamics including independent component analysis , 2004, Journal of Neuroscience Methods.

[33]  Kurt S. Riedel,et al.  Optimal data-based kernel estimation of evolutionary spectra , 1993, IEEE Trans. Signal Process..

[34]  M. B. Priestley,et al.  Design Relations for Non‐Stationary Processes , 1966 .

[35]  Mark P. Taylor,et al.  An empirical examination of long-run purchasing power parity using cointegration techniques , 1988 .

[36]  Walter Enders,et al.  ARIMA and Cointegration Tests of PPP under Fixed and Flexible Exchange Rate Regimes , 1988 .

[37]  Rainer Dahlhaus,et al.  A Likelihood Approximation for Locally Stationary Processes , 2000 .

[38]  Guy Nason,et al.  Simulation Study Comparing Two Tests of Second-order Stationarity and Confidence Intervals for Localized Autocovariance , 2016, 1603.06415.

[39]  W. Crowder,et al.  Testing Stationarity of Real Exchange Rates using Johansen Tests , 2001 .

[40]  U. Grenander,et al.  Statistical analysis of stationary time series , 1957 .

[41]  Guy Melard,et al.  CONTRIBUTIONS TO EVOLUTIONARY SPECTRAL THEORY , 1989 .

[42]  Howell Tong,et al.  On the Analysis of Bivariate Non‐Stationary Processes , 1973 .

[43]  G. Nason,et al.  Wavelet processes and adaptive estimation of the evolutionary wavelet spectrum , 2000 .

[44]  M. Friedman.  A Comparison of Alternative Tests of Significance for the Problem of $m$ Rankings , 1940 .

[45]  D. B. Preston.  Spectral Analysis and Time Series , 1983 .

[46]  Frank Yates,et al.  The Analysis of Multiple Classifications with Unequal Numbers in the Different Classes , 1934 .

[47]  Murray Rosenblatt,et al.  Prolate spheroidal spectral estimates , 2008 .