Whole-brain multivariate prediction

Contributed by ycleong on March 15, 2018

Collection: Neural detection of socially valued community members

Description: We repeated the multivariate prediction analysis across 100 ROIs taken from a whole-brain functional parcellation (Craddock et al., 2011). For each ROI, we performed the same leave-one-participant-out cross-validated prediction analysis and computed the root mean squared error (RMSE) of the prediction for each participant. We then tested the RMSE against chance, defined as the RMSE if the algorithm always predicted the mean hub category, to obtain a t-statistic and p-value for each ROI. Craddock, R. C., James, G. A., Holtzheimer, P. E., Hu, X. P., & Mayberg, H. S. (2012). A whole brain fMRI atlas generated via spatially constrained spectral clustering. Human brain mapping, 33(8), 1914-1928.

Task View 3D View