compute the mean and stddev of your covariate, subtract the mean from each covariate, and then divide the result by stddev.


On 9/28/16 3:47 PM, kinson li wrote:
Hi Greve

Thanks for your reply, can I have more detail about how to solve my problem. By the way, I may not think it's the problem about covariates. 

Thank you.
Jin

2016-09-28 15:29 GMT-04:00 Douglas Greve <greve@nmr.mgh.harvard.edu>:

Try normalizing your covariates (ie, subtract the mean and divide by the stddev).


On 9/28/16 3:07 PM, kinson li wrote:
Hi there, 

Anyone can help me out?  Thank you. 

2016-09-28 13:46 GMT-04:00 kinson li <kinsonljc@gmail.com>:

Hello,

I would like to conduct an analysis using mri_glmfit but I'm getting this error:

ERROR: matrix is ill-conditioned or badly scaled, condno = 1e+08

I am appreciated you can help me solve this problem. 

My command was:

mri_glmfit --y age9vs8ml01.mgh --fsgd new.fsgd dods --C age9vs8mlmatrix.mtx --surf fsaverage lh --cortex  --glmdir glmdir.age9vs8ml


Design matrix ------------------

 1.000   0.000   8.000   0.000;

 1.000   0.000   8.000   0.000;

 1.000   0.000   8.000   0.000;

 1.000   0.000   8.000   0.000;

 1.000   0.000   8.000   0.000;

 1.000   0.000   8.000   0.000;

 1.000   0.000   8.000   0.000;

 1.000   0.000   8.000   0.000;

 1.000   0.000   8.000   0.000;

 1.000   0.000   8.000   0.000;

 1.000   0.000   8.000   0.000;

 1.000   0.000   8.000   0.000;

 1.000   0.000   8.000   0.000;

 1.000   0.000   8.000   0.000;

 1.000   0.000   8.000   0.000;

 1.000   0.000   8.000   0.000;

 1.000   0.000   8.000   0.000;

 1.000   0.000   8.000   0.000;

 0.000   1.000   0.000   9.000;

 0.000   1.000   0.000   9.000;

 0.000   1.000   0.000   9.000;

 0.000   1.000   0.000   9.000;

 0.000   1.000   0.000   9.000;

 0.000   1.000   0.000   9.000;

 0.000   1.000   0.000   9.000;

 0.000   1.000   0.000   9.000;

 0.000   1.000   0.000   9.000;

 0.000   1.000   0.000   9.000;

 0.000   1.000   0.000   9.000;

 0.000   1.000   0.000   9.000;

 0.000   1.000   0.000   9.000;

 0.000   1.000   0.000   9.000;

 0.000   1.000   0.000   9.000;

 0.000   1.000   0.000   9.000;

 0.000   1.000   0.000   9.000;

 0.000   1.000   0.000   9.000;

 0.000   1.000   0.000   9.000;

 0.000   1.000   0.000   9.000;

 0.000   1.000   0.000   9.000;

 0.000   1.000   0.000   9.000;

 0.000   1.000   0.000   9.000;

 0.000   1.000   0.000   9.000;

 0.000   1.000   0.000   9.000;

 0.000   1.000   0.000   9.000;

 0.000   1.000   0.000   9.000;

 0.000   1.000   0.000   9.000;

 0.000   1.000   0.000   9.000;

 0.000   1.000   0.000   9.000;

 0.000   1.000   0.000   9.000;

 0.000   1.000   0.000   9.000;

 0.000   1.000   0.000   9.000;

 0.000   1.000   0.000   9.000;

 0.000   1.000   0.000   9.000;

 0.000   1.000   0.000   9.000;

 0.000   1.000   0.000   9.000;

 0.000   1.000   0.000   9.000;

 0.000   1.000   0.000   9.000;

 0.000   1.000   0.000   9.000;

 0.000   1.000   0.000   9.000;

 0.000   1.000   0.000   9.000;

 0.000   1.000   0.000   9.000;

 0.000   1.000   0.000   9.000;

 0.000   1.000   0.000   9.000;

--------------------------------

ERROR: matrix is ill-conditioned or badly scaled, condno = 1e+08

--------------------------------


Thanks 

Jincheng.





_______________________________________________
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.
_______________________________________________
Freesurfer mailing list
Freesurfer@nmr.mgh.harvard.edu
https://mail.nmr.mgh.harvard.edu/mailman/listinfo/freesurfer