Kernel canonical-correlation Granger causality for multiple time series

Phys Rev E Stat Nonlin Soft Matter Phys. 2011 Apr;83(4 Pt 1):041921. doi: 10.1103/PhysRevE.83.041921. Epub 2011 Apr 25.

Abstract

Canonical-correlation analysis as a multivariate statistical technique has been applied to multivariate Granger causality analysis to infer information flow in complex systems. It shows unique appeal and great superiority over the traditional vector autoregressive method, due to the simplified procedure that detects causal interaction between multiple time series, and the avoidance of potential model estimation problems. However, it is limited to the linear case. Here, we extend the framework of canonical correlation to include the estimation of multivariate nonlinear Granger causality for drawing inference about directed interaction. Its feasibility and effectiveness are verified on simulated data.

Publication types

  • Research Support, Non-U.S. Gov't

MeSH terms

  • Algorithms*
  • Causality
  • Computer Simulation
  • Models, Statistical*
  • Multivariate Analysis