In theory, WLS is the optimal estimator in the case where variance
differs across subject. The FS implementation actually computes
"psuedo-WLS" in which the weights are just the inverse of the first
level variance. A true WLS would use the random effect variance plus the
lower level variance. The first level variance is determined from the
variance of the fMRI time series.
doug
On 4/13/15 6:42 PM, ye tian wrote:
Hello Freesurfers,
I would like to be a little more specific about my question. Was
heteroskedasticity a reason for Weighted Least Square (WLS)? If so,
how did Freesurfer determine the weights?
Thank you!
Sincerely,
Ye
On Mon, Apr 13, 2015 at 4:59 PM, ye tian <tianye...@gmail.com
<mailto:tianye...@gmail.com>> wrote:
Dear Freesurfers,
Can someone please explain to me why WLS was chosen as the method
of regression?
Thank you very much!
Sincerely,
Ye
_______________________________________________
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 Partners Compliance HelpLine at
http://www.partners.org/complianceline . If the e-mail was sent to you in error
but does not contain patient information, please contact the sender and properly
dispose of the e-mail.
