Testing for nonlinearity in time series: the method of surrogate data

https://doi.org/10.1016/0167-2789(92)90102-SGet rights and content

Abstract

We describe a statistical approach for identifying nonlinearity in time series. The method first specifies some linear process as a null hypothesis, then generates surrogate data sets which are consistent with this null hypothesis, and finally computes a discriminating statistic for the original and for each of the surrogate data sets. If the value computed for the original data is significantly different than the ensemble of values computed for the surrogate data, then the null hypothesis is rejected and nonlinearity is detected. We discuss various null hypotheses and discriminating statistics. The method is demonstrated for numerical data generated by known chaotic systems, and applied to a number of experimental time series which arise in the measurement of superfluids, brain waves, and sunspots; we evaluate the statistical significance of the evidence for nonlinear structure in each case, and illustrate aspects of the data which this approach identifies.

References (73)

  • A.R. Osborne et al.

    Physica D

    (1986)
  • A.R. Osborne et al.

    Physica D

    (1989)
  • A. Provenzale et al.

    Physica D

    (1991)
  • J. Theiler

    Phys. Lett. A

    (1991)
  • J.B. Ramsey et al.

    Phys. Lett. A

    (1989)
  • J. Theiler

    J. Opt. Soc. Am. A

    (1990)
  • P. Grassberger et al.

    Physica D

    (1983)
  • S. Ellner

    Phys. Lett. A

    (1988)
  • M. Casdagli
  • D. Nychka et al.

    J. R. Stat. Soc. B

    (1992)
  • R.B. Blackman et al.

    The Measurement of Power Spectra

    (1959)
  • P.E. Rapp et al.

    Brain Topography

    (1989)
  • W.A. Brock et al.

    Nonlinear Modeling and Forecasting

  • C. Nicolis et al.

    Nature

    (1984)
  • P. Grassberger

    Nature

    (1986)
  • C. Nicolis et al.

    Nature

    (1987)
  • P. Grassberger

    Nature

    (1987)
  • G. Mayer-Kress
  • J. Theiler

    Phys. Rev. A

    (1990)
  • F. Takens

    Dynamical Systems and Bifurcations

    (1984)
  • W.E. Caswell et al.

    Dimensions and Entropies in Chaotic Systems - Quantification of Complex Behavior

  • J. Holzfuss et al.

    Dimensions and Entropies in Chaotic Systems - Quantification of Complex Behavior

  • J. Theiler

    Quantifying Chaos: Practical Estimation of the Correlation Dimension

  • M. Möller et al.

    Phys. Lett. A

    (1989)
  • R.L. Smith

    Nonlinear Modeling and Forecasting

  • J. Theiler et al.

    Nonlinear Modeling and Forecasting

  • T. Subba Rao et al.

    J. Time Series Anal.

    (1980)
  • M.J. Hinich

    J. Time Series Anal.

    (1982)
  • A.I. McLeod et al.

    J. Time Series Anal.

    (1983)
  • D.M. Keenan

    Biometrika

    (1985)
  • R.S. Tsay

    Biometrika

    (1986)
  • R.S. Tsay

    Stat. Sin.

    (1991)
  • H. Tong

    Non-linear Time Series: A Dynamical System Approach

    (1990)
  • B. Efron

    SIAM Rev.

    (1979)
  • R.S. Tsay

    Appl. Stat.

    (1992)
  • J.A. Scheinkman et al.

    J. Business

    (1989)
  • Cited by (0)

    View full text