The power of surrogate data testing with respect to non-stationarity

Abstract

Surrogate data testing is a method frequently applied to evaluate the results of nonlinear time series analysis. Since the null hypothesis tested against is a linear, gaussian, stationary stochastic process a positive outcome may not only result from an underlying nonlinear or even chaotic system, but also from e.g. a non-stationary linear one. We investigate the power of the test against non-stationarity.

4 pages, 4 figures, to appear in PRE

Cited by in corpus (11)

• Surrogate time series
• A Comprehensive Spectral and Variability Study of Narrow-Line Seyfert 1 Galaxies Observed by ASCA: I. Observations and Time Series Analysis
• Linear and nonlinear time series analysis of the black hole candidate Cygnus X-1
• What can be inferred from surrogate data testing?
• Observational Window Functions in Planet Transit Surveys
• Local Analysis of Dissipative Dynamical Systems
• Detecting frequency modulation in stochastic time series data
• Combining the ApEn statistic with surrogate data analysis for the detection of nonlinear dynamics in time series
• Surrogate data for non-stationary signals
• A simple method for detecting chaos in nature
• Band-phase-randomized Surrogates to assess nonlinearity in non-stationary time series