This repository contains the code for the VEVAR (Bayesian Varying-Effects Vector Autoregressive) algorithm as described in the manuscript accepted for publication in Human Brain Mapping:
"Bayesian Varying-Effects Vector Autoregressive Models for Inference of Brain Connectivity Networks and Covariate Effects in Pediatric Traumatic Brain Injury."
Authors: Yangfan Ren, Nathan Osborne, Christine B. Peterson, Dana M. DeMaster, Linda Ewing-Cobbs, and Marina Vannucci
The VEVAR algorithm is implemented in Python and is designed for analyzing brain connectivity networks and the effects of covariates in pediatric traumatic brain injury.
VEVAR_functions.py: Contains all helper functions and the main function for the VEVAR algorithm.Data_gen.ipynb: Jupyter notebook for generating simulation data.data.mat: Sample simulated data file.Demo.ipynb: A demonstration notebook for running the VEVAR algorithm using simulated data.Demo.html: HTML version of the Demo notebook.Network_plot.R: R script for generating inferred network plots.ROI_names.mat: Example ROI names used in the plots.
For detailed instructions on how to use the VEVAR functions and perform further inference, please refer to Demo.ipynb.
Yangfan Ren, Nathan Osborne