cosanlab/nltools
Improve auto-correlation estimation during regression
Chiusa
#307 aperta il 22 lug 2019
enhancementhelp wanted
Metriche repository
- Star
- (130 stelle)
- Metriche merge PR
- (Nessuna PR mergiata in 30 g)
Descrizione
Currently, we do a pretty crude ARMA model if the user wants to model auto-correlations. We have a few options to improve this:
- AFNI style: implement our own limited grid search of ARMA parameters per voxel rather than unconstrained optimization in statsmodels (currrent) - probably the trickiest and slowest
- Implement pre-whitening routines by first estimating OLS, then using the residuals of order N to adjust the data, and finally fit OLS again. Nistats has an implentation of this: see this and this.
- Port over SPMs new FAST routine which does something like using basis-sets of covariance matrices to account for auto-correlation