A General Comovement Measure for Time Series

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

Abstract

We propose a nonparametric, time-dependent, cross-scale/cross-frequency dependence measure for multivariate stationary and non-stationary time series termed multi-thickness thick pen measure of association, MTTPMA. The building blocks of the measure are the Thick Pen Transform and the Thick Pen Measure of Association. The new measure is simple and visually interpretable. We demonstrate its potential application on synthetic financial contagion data.
Original languageEnglish
Title of host publicationMathematical and Statistical Methods for Actuarial Sciences and Finance : eMAF2020
EditorsMarco Corazza, Manfred Gilli, Cira Perna, Claudio Pizzi, Marilena Sibillo
Place of PublicationCham
PublisherSpringer
Publication date2021
Edition1
Pages279-284
ISBN (Print)978-3-030-78964-0, 978-3-030-78967-1
ISBN (Electronic)978-3-030-78965-7
DOIs
Publication statusPublished - 2021
MoE publication typeA4 Article in conference proceedings

Publication series

NameMathematical and Statistical Methods for Actuarial Sciences and Finance

Keywords

  • 112 Statistics and probability
  • cross-scale
  • multiscale
  • multivariate
  • nonparametric
  • time-varying

Fingerprint

Dive into the research topics of 'A General Comovement Measure for Time Series'. Together they form a unique fingerprint.

Cite this