The Multivariate Granger Causality (MVGC) Toolbox

The MVGC Multivariate Granger Causality Toolbox facilitates Granger-causal inference from time-series data.

This is the MVGC Multivariate Granger Causality MATLAB toolbox, previously hosted at http://www.sussex.ac.uk/sackler/mvgc

Current version is mvgc_v1.3, last updated March 2022

NOTE: this version includes an implementation of the new, more efficient and accurate state-space method for GC calculation, as detailed in:

L. Barnett and A. K. Seth, Granger causality for state-space models,
Phys. Rev. E 91(4) Rapid Communication, 2015.

See the file: mvgc_demo_statespace.m in the demo subdirectory.

This toolbox, developed at the Sackler Centre for Consciousness Science, University of Sussex, UK, provides MATLAB routines for efficient and accurate estimation and statistical inference of multivariate Granger causality from time-series data, as described in:

L. Barnett and A. K. Seth, "The MVGC Multivariate Granger Causality Toolbox: A new
approach to Granger-causal inference", J. Neurosci. Methods 223, pp 50-68, 2014.

For general support issues, comments, questions, bug reports and suggested enhancements, please email [e-mail]. We would especially like to know if you have found the toolbox useful in your research.

Please note that this software is provided freely under the GNU General Public License (version 3) and is for use at your own risk.