Multiscale reconstruction of time series

Abstract

A new method is proposed which allows a reconstruction of time series based on higher order multiscale statistics given by a hierarchical process. This method is able to model the time series not only on a specific scale but for a range of scales. It is possible to generate complete new time series, or to model the next steps for a given sequence of data. The method itself is based on the joint probability density which can be extracted directly from given data, thus no estimation of parameters is necessary. The results of this approach are shown for a real world dataset, namely for turbulence. The unconditional and conditional probability densities of the original and reconstructed time series are compared and the ability to reproduce both is demonstrated. Therefore in the case of Markov properties the method proposed here is able to generate artificial time series with correct n-point statistics.

4 pages, 3 figures

References in corpus (7)

• Modelling fluctuations of financial time series: from cascade process to stochastic volatility model
• Dynamical model and nonextensive statistical mechanics of a market index on large time windows
• Stochastic Analysis and Regeneration of Rough Surfaces
• Markov properties of high frequency exchange rate data
• An Iterative Procedure for the Estimation of Drift and Diffusion Coefficients of Langevin Processes
• Stochastic analysis of surface roughness
• Increment definitions for scale dependent analysis of stochastic data

Cited by in corpus (11)

• Wind Energy and the Turbulent Nature of the Atmospheric Boundary Layer
• The Fokker-Planck Approach to Complex Spatio-Temporal Disordered Systems
• A dissipative random velocity field for fully developed fluid turbulence
• Improved estimation of Fokker-Planck equations through optimisation
• An open source MATLAB package to perform basic and advanced statistical analysis of turbulence data and other complex systems
• Analytic reconstruction of some dynamical systems
• Multi-level stochastic refinement for complex time series and fields: A Data-Driven Approach
• Medium and Small Scale Analysis of Financial Data
• Recurrence flow measure of nonlinear dependence
• A multiscale and multicriteria Generative Adversarial Network to synthesize 1-dimensional turbulent fields
• Analysis of Multipoint Correlations in Direct Numerical Simulation