Partial Mutual Information for Coupling Analysis of Multivariate Time Series

Stefan Frenzel and Bernd Pompe
Phys. Rev. Lett. 99, 204101 – Published 14 November 2007

Abstract

We propose a method to discover couplings in multivariate time series, based on partial mutual information, an information-theoretic generalization of partial correlation. It represents the part of mutual information of two random quantities that is not contained in a third one. By suitable choice of the latter, we can differentiate between direct and indirect interactions and derive an appropriate graphical model. An efficient estimator for partial mutual information is presented as well.

  • Figure
  • Figure
  • Figure
  • Figure
  • Received 23 May 2007

DOI:https://doi.org/10.1103/PhysRevLett.99.204101

©2007 American Physical Society

Authors & Affiliations

Stefan Frenzel and Bernd Pompe

  • Institute of Physics, University of Greifswald, D-17487 Greifswald, Germany

Article Text (Subscription Required)

Click to Expand

References (Subscription Required)

Click to Expand
Issue

Vol. 99, Iss. 20 — 16 November 2007

Reuse & Permissions
Access Options
Author publication services for translation and copyediting assistance advertisement

Authorization Required


×
×

Images

×

Sign up to receive regular email alerts from Physical Review Letters

Log In

Cancel
×

Search


Article Lookup

Paste a citation or DOI

Enter a citation
×