Skip to main content
. 2020 Oct 15;220:117127. doi: 10.1016/j.neuroimage.2020.117127

Fig. 8.

Fig. 8

The p-values for the K–S test for the comparison between the validation set harmonized with Neuroharmony and the training sample harmonized with ComBat. From left to right, each bar in the pairs of bars represents the p-value of the K–S test for the data corrected by Neuroharmony (green) and the data without any correction (red, filled with dots). A horizontal black dashed line marks the 0.001 threshold.