About the statistics of the classification(decoding)

Hi, I want to know how can I do the cluster-based permutation test in the decoding accuracy, so that I can find the onset time point of the decoding time-series.

Thank you~

I am not sure I understand the details of your request, esp. which clusters you would be running the permutation test on. That being said, the decoding accuracy process in Brainstorm can premutation procedure that yields estimates of error bars around the mean accuracy stat at every time point. You can derive the estimation of the "start point" based on these estimates.