Discrimination power of measures for nonlinearity in a time series

Abstract

The performance of a number of different measures of nonlinearity in a time series is compared numerically. Their power to distinguish noisy chaotic data from linear stochastic surrogates is determined by Monte Carlo simulation for a number of typical data problems. The main result is that the ratings of the different measures vary from example to example. It seems therefore preferable to use an algorithm with good overall performance, that is, higher order autocorrelations or nonlinear prediction errors.

6 pages, 2 figures

References in corpus (1)

• Improved surrogate data for nonlinearity tests

Cited by in corpus (27)

• Surrogate time series
• Practical implementation of nonlinear time series methods: The TISEAN package
• Nonlinear time-series analysis revisited
• Constrained randomization of time series data
• Nonlinear Mode Decomposition: a new noise-robust, adaptive decomposition method
• Analysing Large Scale Structure: I. Weighted Scaling Indices and Constrained Randomisation
• Surrogate Test to Distinguish between Chaotic and Pseudoperiodic Time Series
• Revisiting algorithms for generating surrogate time series
• On the Nature of X-ray Variability in Ark 564
• Testing for nonlinearity in unevenly sampled time series
• A Machine Learning Classifier for Microlensing in Wide-Field Surveys
• A multifractal surrogate data generation algorithm that preserves pointwise Holder regularity structure, with initial applications to turbulence
• Surrogate-assisted network analysis of nonlinear time series
• Recurrence network measures for hypothesis testing using surrogate data: application to black hole light curves
• Spectral and Time Series Analyses of the Seyfert 1 AGN: Zw 229.015
• Characterizing black hole variability with nonlinear methods: the case of the X-ray Nova 4U 1543-47
• Local Analysis of Dissipative Dynamical Systems
• Measures of Analysis of Time Series (MATS): A MATLAB Toolkit for Computation of Multiple Measures on Time Series Data Bases
• Time Series with Tailored Nonlinearities
• The turbulence velocity gradient tensor formed additively by normal and non-normal tensors
• Phase Walk Analysis of Leptokurtic Time Series
• Identifying statistical indicators of temporal asymmetry using a data-driven approach
• Interplay of transitions between oscillations with emergence of fireballs and quantification of phase coherence, scaling index in a magnetized glow discharge plasma of toroidal assembly
• Bursts of extensive air showers: chaos vs. stochasticity
• Waves and distributions connected to systems of interacting populations
• Constrained randomization of time series for hypothesis testing
• Network Abstractions of Prescription Patterns in a Medicaid Population