• Corpus ID: 88512109

Band-phase-randomized Surrogates to assess nonlinearity in non-stationary time series

  title={Band-phase-randomized Surrogates to assess nonlinearity in non-stationary time series},
  author={Diego Luis Guar{\'i}n and Edilson Delgado and {\'A}lvaro Orozco},
  journal={arXiv: Applications},
Abstract—Testing for nonlinearity is one of the most importantpreprocessing steps in nonlinear time series analysis. Typically,this is done by means of the linear surrogate data methods.But it is a known fact that the validity of the results heavilydepends on the stationarity of the time series. Since mostphysiological signals are non-stationary, it is easy to falsely detectnonlinearity using the linear surrogate data methods. In thisdocument, we propose a methodology to extend the procedurefor… 

Figures from this paper


Time-Varying Surrogate Data to Assess Nonlinearity in Nonstationary Time Series: Application to Heart Rate Variability
Analysis of simulated time series showed that using TIV surrogates, linear nonstationary time series may be erroneously regarded as nonlinear and weak TV nonlinearities may remain unrevealed, while the use of TV AR surrogates markedly increases the probability of a correct interpretation.
A Method for the Time-Varying Nonlinear Prediction of Complex Nonstationary Biomedical Signals
The method is used in conjunction with a TV surrogate method to provide statistical validation that the presence of nonlinearity is not due to nonstationarity itself and provides reasonable nonlinear prediction even for TV deterministic chaotic signals.
A wavelet-based method for surrogate data generation
Detecting Nonlinearity in Data with Long Coherence Times
The limitations of two techniques for detecting nonlinearity in time series are considered and some initial evidence for nonlinear structure in the SFI dataset E is seen, although it is inclined to dismiss this evidence as an artifact of the long coherence time.
Power of surrogate data testing with respect to nonstationarity
This work investigates the power of the test against non-stationarity, a method frequently applied to evaluate the results of nonlinear time series analysis, against a linear, gaussian, stationary stochastic process.
Surrogate time series
Improved Surrogate Data for Nonlinearity Tests.
It is shown that nonlinear rescalings of a Gaussian linear stochastic process cannot be accounted for by a simple amplitude adjustment of the surrogates which leads to spurious detection of nonlinearity.
Constrained-realization Monte-Carlo method for hypothesis testing
Surrogate data for non-stationary signals
This work addresses the problem of generating proper surrogate data corresponding to the null hypothesis of an ARMA process with slowly varying coefficients to distinguish nonlinearity from non-stationarity.