Abstract
Stationarity is a crucial yet rarely questioned assumption in the analysis of time series of magneto- (MEG) or electroencephalography (EEG). One key drawback of the commonly used tests for stationarity of encephalographic time series is the fact that conclusions on stationarity are only indirectly inferred either from the Gaussianity (e.g. the Shapiro–Wilk test or Kolmogorov–Smirnov test) or the randomness of the time series and the absence of trend using very simple time-series models (e.g. the sign and trend tests by Bendat and Piersol). We present a novel approach to the analysis of the stationarity of MEG and EEG time series by applying modern statistical methods which were specifically developed in econometrics to verify the hypothesis that a time series is stationary. We report our findings of the application of three different tests of stationarity—the Kwiatkowski–Phillips–Schmidt–Schin (KPSS) test for trend or mean stationarity, the Phillips–Perron (PP) test for the presence of a unit root and the White test for homoscedasticity—on an illustrative set of MEG data. For five stimulation sessions, we found already for short epochs of duration of 250 and 500 ms that, although the majority of the studied epochs of single MEG trials were usually mean-stationary (KPSS test and PP test), they were classified as nonstationary due to their heteroscedasticity (White test). We also observed that the presence of external auditory stimulation did not significantly affect the findings regarding the stationarity of the data. We conclude that the combination of these tests allows a refined analysis of the stationarity of MEG and EEG time series.
Article PDF
Similar content being viewed by others
Avoid common mistakes on your manuscript.
References
Barlow JS (1985) Methods of analysis of nonstationary EEGs, with emphasis on segmentation techniques: a comparative review. J Clin Neurophysiol 2:267–304
Bendat JS, Piersol AG (1966) Measurement and analysis of random data. Wiley, New York
Bendat JS, Piersol AG (1986) Random data: analysis and measurement procedures. Wiley, New York
Bender R, Schultz B, Schultz A, Pichlmayr I (1992) Testing the gaussianity of the human EEG during anesthesia. Methods Inf Med 31: 56–59
Bollerslev T (1986) Generalized autoregressive conditional heteroskedasticity. J Econom 31: 307–327
Box GEP, Jenkins GM (1970) Time series analysis, forecasting and control. Holden-Day, Oakland
Brockwell PJ, Davis RA (2002) Introduction to time series and forecasting. Springer, New York
Cohen BA, Sances A (1977) Stationarity of the human electroencephalogram. Med Biol Eng Comput 15: 513–518
Dickey D, Fuller W (1979) Distribution of the estimators for autoregressive time series with a unit root. J Am Stat Assoc 74: 427–431
Durka PJ (2007) Matching prsuit and unification in EEG analysis Engineering in medicine and biology. Artech House, Boston
Galka A, Yamashita O, Ozaki T (2004a) Garch modelling of covariance in dynamical estimation of inverse solutions. Phys Lett A 333: 261–268
Galka A, Yamashita O, Ozaki T, Biscay R, Valdes-Sosa P (2004b) A solution to the dynamical inverse problem of EEG generation using spatiotemporal kalman filtering. Neuroimage 23: 435–453
Gasser T, Molinari L (1996) The analysis of the EEG. Stat Methods Med Res 5: 67–99
Gersch W (1970) Spectral analysis of EEGs by autoregressive decomposition of time series. Math Biosci 7: 205–222
Kaplan AY (1999) The problem of segmental description of human electroencephalogram. Human Physiol 25: 107–114
Kawabata N (1976) Test of statistical stability of the electroencephalogram. Biol Cybern 22: 235–238
König R, Sielużycki C, Simserides C, Heil P, Scheich H (2008) Effects of the task of categorizing FM direction on auditory evoked magnetic fields in the human auditory cortex. Brain Res 1220: 102–117
Krystal A, Prado R, West M (1999) New methods of time series analysis of non-stationary EEG data: Eigenstructure decomposition of time varying autoregressions. http://citeseer.ist.psu.edu/krystal99new.html
Kwiatkowski D, Phillips PCB, Schmidt P, Shin Y (1992) Testing the null hypothesis of stationarity against the alternative of a unit root. J Econom 54: 159–178
McEwen JA, Anderson GB (1975) Modeling the stationarity and gaussianity of spontaneous electroencephalographic activity. IEEE Trans Biomed Eng 22: 361–369
Möcks J, Pham DT, Gasser T (1984) Testing for homogeneity of noisy signals evoked by repeated stimuli. Ann Stat 12: 193–209
Möcks J, Gasser T, Pham DT (1984) Variability of single visual evoked potentials, evaluated by two new statistical tests. Electroencephalogr Clin Neurophysiol 57: 571–580
Näätänen R, Picton T (1987) The N1 wave of the human electric and magnetic response to sound: a review and an analysis of the component structure. Psychophysiology 24(4): 375–425
Newey WK, West KD (1987) A simple, positive semi-definite, heteroskedasticity and autocorrelation consistent covariance matrix. Econometrica 55: 703–708
Ozaki T, Wong K, Galka A, John R (2006) Recent surge of time series methods in neuroscience—causal modeling and time-varying innovation variances. http://www.taniguchi.sci.waseda.ac.jp/Waseda_Workshop_2006/Proceedings/Ozaki/Ozaki_1.pdf
Pantula SG (1989) Testing for unit roots in time series data. Econom Theor 5(2): 256–271
Perron P (1988) Trends and random walks in macroeconomic time series. J Econom Dyn Control 12: 297–332
Phillips PCB (1987) Time series regression with a unit root. Econometrica 55: 277–301
Phillips PCB., Perron P. (1988) Testing for a unit root in time series regression. Biometrika 75: 335–346
Said SE, Dickey DA (1984) Testing for unit roots in autoregressive-moving average models of unknown order. Biometrika 71: 599–608
Saikkonen P (1993) A note on a Lagrange multiplier test for testing an autoregressive unit root. Econom Theor 9: 494–498
Shumway RH, Stoffer DS (2000) Time series analysis and its applications. Springer, New York
Sielużycki C., König R., Matysiak A., Kuś R., Durka PJ. (2009a) Single-trial evoked brain responses modeled by multivariate matching pursuit. IEEE Trans Biomed Eng 56(1): 74–82
Sielużycki C, Kuś R, Matysiak A, Durka PJ, König R (2009b) Multivariate matching pursuit in the analysis of single-trial latency of the auditory M100 acquired with MEG. Int J Bioelectromagn 11(4): 155–160
Tanaka K (1983) Non-normality of the Lagrange multiplier statistic for testing the constancy of regression coefficients. Econometrica 51: 1577–1582
Trapletti A, Hornik K (2011) tseries: Time series analysis and computational finance. R package version 0.10-25. http://CRAN.R-project.org/package=tseries
Weiss M (2005) Testing correlated EEG-like data for normality using a modified Kolmogorov–Smirnov statistic. J Econom 128: 195–213
White H (1980) A heteroskedasticity-consistent covariance matrix estimator and a direct test for homoskedasticity. Econometrica 48: 817–838
Wong KF, Galka A, Yamashita O, Ozaki T (2005) Modelling non-stationary variance in EEG time series by state space garch model. Comput Biol Med 36: 1327–1335
Wright JJ, Kydd RR, Sergejew AA (1990) Autoregression models of EEG—results compared with expectations for a multilinear near-equilibrium biophysical process. Biol Cybern 62: 201–210
Acknowledgments
We would like to thank Norman Zacharias for the realization of the MEG measurement.
Open Access
This article is distributed under the terms of the Creative Commons Attribution Noncommercial License which permits any noncommercial use, distribution, and reproduction in any medium, provided the original author(s) and source are credited.
Author information
Authors and Affiliations
Corresponding author
Additional information
L. Kipiński and W. Kordecki formerly at Wrocław University of Technology.
Rights and permissions
Open Access This is an open access article distributed under the terms of the Creative Commons Attribution Noncommercial License (https://creativecommons.org/licenses/by-nc/2.0), which permits any noncommercial use, distribution, and reproduction in any medium, provided the original author(s) and source are credited.
About this article
Cite this article
Kipiński, L., König, R., Sielużycki, C. et al. Application of modern tests for stationarity to single-trial MEG data. Biol Cybern 105, 183–195 (2011). https://doi.org/10.1007/s00422-011-0456-4
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00422-011-0456-4