Please check the Wiki for the latest documentation, including some basic introduction to the method.
The example.m file provides some basic demonstration of the toolbox functionality. The run_HMMMAR.m is a template script that specifies some basic options depending on the specified data modality and, provided that the user has already loaded the data in the right format (see the script for details), runs the HMM-MAR and gets some basic information out of the estimation.
For more detailed description and simulations, please refer to
Diego Vidaurre, Andrew J. Quinn, Adam P. Baker, David Dupret, Alvaro Tejero-Cantero and Mark W. Woolrich Spectrally resolved fast transient brain states in electrophysiological data. NeuroImage. Volume 126, 1 February 2016, Pages 81–95.
Diego Vidaurre, Romesh Abeysuriya, Robert Becker, Andrew J. Quinn, F. Alfaro-Almagro, S.M Smith and Mark W. Woolrich Discovering dynamic brain networks from big data in rest and task. NeuroImage. June 2017