A periodogram-based test for weak stationarity and consistency between sections in time series

In one approach to spectral estimation, a sample record is broken into a number of disjoint sections, or data is collected over a number of discrete trials. Spectral parameters are formed by averaging periodograms across these discrete sections or trials. A key assumption in this approach is that of weak stationarity. This paper describes a simple test that checks if periodogram ordinates are consistent across sections as a means of assessing weak stationarity. The test is called the Periodogram Coefficient of Variation (PCOV) test, and is a frequency domain test based on a technique of spectral analysis. Application of the test is illustrated to both simulated and experimental data (EMG, physiological tremor, EEG). An additional role for the test as a useful tool in exploratory analysis of time series is highlighted.

[1]  C. D. Kemp,et al.  Kendall's Advanced Theory of Statistics, Vol. 1: Distribution Theory. , 1995 .

[2]  C. Vaughan,et al.  Rectification and non-linear pre-processing of EMG signals for cortico-muscular analysis , 2003, Journal of Neuroscience Methods.

[3]  A. Rigas,et al.  A semi-parametric approach for comparing the estimated spectra of two stationary point processes. , 2007, Mathematical biosciences.

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

[5]  A M Amjad,et al.  A framework for the analysis of mixed time series/point process data--theory and application to the study of physiological tremor, single motor unit discharges and electromyograms. , 1995, Progress in biophysics and molecular biology.

[6]  J. R. Rosenberg,et al.  On the application, estimation and interpretation of coherence and pooled coherence , 2000, Journal of Neuroscience Methods.

[7]  Peter J. Diggle,et al.  Spectral Analysis of Replicated Biomedical Time Series , 1997 .

[8]  A.H. Nuttall,et al.  Spectral estimation using combined time and lag weighting , 1982, Proceedings of the IEEE.

[9]  J. R. Rosenberg,et al.  Using electroencephalography to study functional coupling between cortical activity and electromyograms during voluntary contractions in humans , 1998, Neuroscience Letters.

[10]  Peter J. Diggle.  Comparing Estimated Spectral Densities Using GLIM , 1985 .

[11]  T. Rao,et al.  An Introduction to Bispectral Analysis and Bilinear Time Series Models , 1984 .

[12]  B. Conway,et al.  Synchronization between motor cortex and spinal motoneuronal pool during the performance of a maintained motor task in man. , 1995, The Journal of physiology.

[13]  P. Mitra,et al.  Analysis of dynamic brain imaging data. , 1998, Biophysical journal.

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

[15]  R. N. Stiles,et al.  Mechanical factors in human tremor frequency. , 1967, Journal of applied physiology.

[16]  J. Kiefer,et al.  An Introduction to Stochastic Processes. , 1956 .

[17]  A. Walden,et al.  Spectral analysis for physical applications : multitaper and conventional univariate techniques , 1996 .

[18]  P. Welch.  The use of fast Fourier transform for the estimation of power spectra: A method based on time averaging over short, modified periodograms , 1967 .

[19]  Partha P. Mitra,et al.  Sampling Properties of the Spectrum and Coherency of Sequences of Action Potentials , 2000, Neural Computation.

[20]  D. Brillinger.  Time series - data analysis and theory , 1981, Classics in applied mathematics.

[21]  F. Varela,et al.  Perception's shadow: long-distance synchronization of human brain activity , 1999, Nature.

[22]  A Power Spectral Estimate which is Insensitive to Transients , 1973 .

[23]  T. Rao,et al.  A TEST FOR LINEARITY OF STATIONARY TIME SERIES , 1980 .

[24]  S. Coles,et al.  Semiparametric models and inference for biomedical time series with extra-variation. , 2001, Biostatistics.

[25]  J. Tukey.  Discussion, Emphasizing the Connection Between Analysis of Variance and Spectrum Analysis* , 1961 .

[26]  J. R. Rosenberg,et al.  The Fourier approach to the identification of functional coupling between neuronal spike trains. , 1989, Progress in biophysics and molecular biology.

[27]  Peter Bloomfield,et al.  Fourier Analysis of Time Series: An Introduction , 1977 .

[28]  T. Rao,et al.  Developments in time series analysis : in honour of Maurice B. Priestley , 1994 .

[29]  J. R. Rosenberg,et al.  Load-independent contributions from motor-unit synchronization to human physiological tremor. , 1999, Journal of neurophysiology.