This is just straight-forward GLM, ie,
beta = inv(X'*X)*X'*y (y is the input time series after preproc)
yhat = X*beta
residual = y - yhat
residualstd = sum(residual.^2)/DOF (DOF = rows of X - cols of X)
t = C*beta/sqrt(C'*inv(X'*X)*C*residualstd)
where C is the contrast matrix
On 3/10/2023 4:50 PM, haora...@gmail.com wrote:
External Email - Use Caution
Hi,
I have a naïve question. When I use GLM for a single subject
timeseries data, how the variance is evaluated to get the t value? I
know the beta values and contrast matrix make the numerator for the t
value. How is the denominator made? Is it through the fitting residual
ie std(residual), or is it from session by session or run by run
variance? Can I find the formula somewhere? I was not able to find the
answer in tutorial or the existing mailing list. Thanks a lot!
Best,
Haoran
_______________________________________________
Freesurfer mailing list
Freesurfer@nmr.mgh.harvard.edu
https://mail.nmr.mgh.harvard.edu/mailman/listinfo/freesurfer
_______________________________________________
Freesurfer mailing list
Freesurfer@nmr.mgh.harvard.edu
https://mail.nmr.mgh.harvard.edu/mailman/listinfo/freesurfer
The information in this e-mail is intended only for the person to whom it is
addressed. If you believe this e-mail was sent to you in error and the e-mail
contains patient information, please contact the Mass General Brigham
Compliance HelpLine at https://www.massgeneralbrigham.org/complianceline
<https://www.massgeneralbrigham.org/complianceline> .
Please note that this e-mail is not secure (encrypted). If you do not wish to
continue communication over unencrypted e-mail, please notify the sender of
this message immediately. Continuing to send or respond to e-mail after
receiving this message means you understand and accept this risk and wish to
continue to communicate over unencrypted e-mail.
