Skip to Main content Skip to Navigation
Journal articles

A model-free characterization of recurrences in stationary time series

Abstract : Study of recurrences in earthquakes, climate, financial time-series, etc. is crucial to better forecast disasters and limit their consequences. Most of the previous phenomenological studies of recurrences have involved only a long-ranged autocorrelation function, and ignored the multi-scaling properties induced by potential higher order dependencies. We argue that copulas is a natural model-free framework to study non-linear dependencies in time series and related concepts like recurrences. Consequently, we arrive at the facts that (i) non-linear dependences do impact both the statistics and dynamics of recurrence times, and (ii) the scaling arguments for the unconditional distribution may not be applicable. Hence, fitting and/or simulating the intertemporal distribution of recurrence intervals is very much system specific, and cannot actually benefit from universal features, in contrast to the previous claims. This has important implications in epilepsy prognosis and financial risk management applications. (C) 2017 Elsevier B.V. All rights reserved.
Document type :
Journal articles
Complete list of metadatas
Contributor : Delphine Le Piolet <>
Submitted on : Wednesday, December 11, 2019 - 9:25:00 AM
Last modification on : Thursday, July 2, 2020 - 9:12:02 AM

Links full text



Remy Chicheportiche, Anirban Chakraborti. A model-free characterization of recurrences in stationary time series. Physica A: Statistical Mechanics and its Applications, Elsevier, 2017, 474, pp.312-318. ⟨10.1016/j.physa.2017.01.073⟩. ⟨hal-02403951⟩



Record views