Constrained randomization of time series data

Abstract

A new method is introduced to create artificial time sequences that fulfil given constraints but are random otherwise. Constraints are usually derived from a measured signal for which surrogate data are to be generated. They are fulfilled by minimizing a suitable cost function using simulated annealing. A wide variety of structures can be imposed on the surrogate series, including multivariate, nonlinear, and nonstationary properties. When the linear correlation structure is to be preserved, the new approach avoids certain artifacts generated by Fourier-based randomization schemes.

4 pages, 2 figures

References in corpus (2)

• Improved surrogate data for nonlinearity tests
• Discrimination power of measures for nonlinearity in a time series

Cited by in corpus (24)

• Surrogate time series
• Practical implementation of nonlinear time series methods: The TISEAN package
• Test your surrogate data before you test for nonlinearity
• The dynamic of information-driven coordination phenomena: a transfer entropy analysis
• Statically Transformed Autoregressive Process and Surrogate Data Test for Nonlinearity
• Phase space embedding of electrocardiograms
• Analysing Large Scale Structure: I. Weighted Scaling Indices and Constrained Randomisation
• Linear and nonlinear time series analysis of the black hole candidate Cygnus X-1
• On the Nature of X-ray Variability in Ark 564
• Testing for nonlinearity in unevenly sampled time series
• Multicanonical MCMC for Sampling Rare Events
• Analysing large scale structure: II. Testing for primordial non-Gaussianity in CMB maps using surrogates
• Using Topological Statistics to Detect Determinism in Time Series
• Sampling rate-corrected analysis of irregularly sampled time series
• Detecting Determinism in High Dimensional Chaotic Systems
• Probing non-Gaussianities in the CMB on an incomplete sky using surrogates
• The human ECG - nonlinear deterministic versus stochastic aspects
• Emerging interdependence between stock values during financial crashes
• Bursts of extensive air showers: chaos vs. stochasticity
• Surrogate data for non-stationary signals
• Surrogate Monte Carlo
• Geometrical approach to modeling of nonlinear systems from experimental data
• Constrained randomization of time series for hypothesis testing
• Band-phase-randomized Surrogates to assess nonlinearity in non-stationary time series