Surrogate data for non-stationary signals

1999/04/13 by Andreas Schmitz, Schmitz, Andreas, Thomas Schreiber +1
Chemistry · Engineering · Physics and Astronomy · #Chaotic Dynamics (nlin.CD) #Control Systems and Identification #FOS: Physical sciences #Fault Detection and Control Systems #Spectroscopy and Chemometric Analyses #chao-dyn #nlin.CD

paper · pdf · doi:10.48550/arxiv.chao-dyn/9904023

4 pages, 4 figures. proceeding for a poster

arxiv created 1999/04/13 · openalex publication_date 1999/04/13 · arxiv updated 2009/11/30 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Standard tests for nonlinearity reject the null hypothesis of a Gaussian linear process whenever the data is non-stationary. Thus, they are not appropriate to distinguish nonlinearity from non-stationarity. We address the problem of generating proper surrogate data corresponding to the null hypothesis of an ARMA process with slowly varying coefficients.

Related

• A new surrogate data method for nonstationary time series
• Surrogate data method applied to nonlinear time series
• Band-phase-randomized Surrogates to assess nonlinearity in non-stationary time series
• On Surrogate Data Testing for Linearity based on the Periodogram
• Combining the ApEn statistic with surrogate data analysis for the detection of nonlinear dynamics in time series