Dear Chao
I have a question regarding you program y_corr2p, that was very useful to me. I would like to know how the P value is calculated. All other algorithms I have been using use the mean(r) and std(r) across all subjects, but your code is independent of the number of subjects, only taking into account the number of time points in the series. I am curious about how it is calculated
best regards
Pablo
Dear Pablo,
"using the mean(r) and std(r) across all subjects" is to test the significance of r on group level. It also can test the significance of r on individual level.
The significance test for Pearson's r is computed as follows:
with N - 2 degrees of freedom, r is Pearson's correlation and N is the number of pairs of scores that went into the computation of r.
Please see more details from http://davidmlane.com/
This function will be added to rest_sliceviewer in the next release.
Best wishes!
Chao-Gan
I have a question regarding you program y_corr2p, that was very useful to me. I would like to know how the P value is calculated. All other algorithms I have been using use the mean(r) and std(r) across all subjects, but your code is independent of the number of subjects, only taking into account the number of time points in the series. I am curious about how it is calculated
best regards
Pablo
Dear Pablo,
"using the mean(r) and std(r) across all subjects" is to test the significance of r on group level. It also can test the significance of r on individual level.
The significance test for Pearson's r is computed as follows:
with N - 2 degrees of freedom, r is Pearson's correlation and N is the number of pairs of scores that went into the computation of r.
Please see more details from http://davidmlane.com/
This function will be added to rest_sliceviewer in the next release.
Best wishes!
Chao-Gan
Forums