Hi both, That makes sense, however, as for my groups, all exceed 10 cases per combination for gender and scanner type (two dichotomous variables). But I also use Follow-time and age as covariate, might I need to recode those, to less unique combinations are possible?
Thanks. Sander -----Oorspronkelijk bericht----- Van: freesurfer-boun...@nmr.mgh.harvard.edu [mailto:freesurfer-boun...@nmr.mgh.harvard.edu] Namens Sanne Oostermeijer Verzonden: donderdag 7 mei 2015 10:02 Aan: freesurfer@nmr.mgh.harvard.edu Onderwerp: Re: [Freesurfer] FW: Re: ERROR: matrix is ill-conditioned or badly scaled Hi Doug, I did. The email below is another FS user having the same error. Sander, I had the same problem due to having only 1 female in one of the groups (and correcting for gender). -----Oorspronkelijk bericht----- Van: freesurfer-boun...@nmr.mgh.harvard.edu [mailto:freesurfer-boun...@nmr.mgh.harvard.edu] Namens Douglas N Greve Verzonden: woensdag 6 mei 2015 17:47 Aan: freesurfer@nmr.mgh.harvard.edu Onderwerp: Re: [Freesurfer] FW: Re: ERROR: matrix is ill-conditioned or badly scaled did you see the email I sent last night about you having one group with only one subject? On 05/06/2015 08:50 AM, Verfaillie, Sander wrote: > > Dear Douglasor colleague, > > Currently I am working on one of the last steps of freesurfer > analyses; the mri_glmdir. > > However, trying multiple FSGD versions and after reading several posts > one this topic on your Harvard webpage, the "ill-conditioned or badly > scaled" message keeps on popping up. > > I have checked the number of lines, column spacing. Furthermore I have > used excel2.txt conversion for creating the FSGD file, which in > previous analyses worked out perfectly fine. > > Command line: mri_glmfit --y rh.age_gender_scanner_FU_time.00.mgh > --fsgd FSGD_v4_2.fsgd dods --C Contrast_test.mtx --surf fsaverage lh > --cortex --glmdir rh.FSGD_v4_2_4covariates.glmdir > > After visual inspection of the Xg.dat file it seems columns are > slightly shifted. I am not sure whether this causes the error. > > rh.FSGD_v4_2_4covariates.glmdir/Xg.dat > > Could you help me out? I have attached the necessary files. Sample > size: n=305, 2 class, 4 covariates > > The aim of this analyses is to look at contrast group1>group2 while > regressing out the effects of gender, scanner type, age and follow-up > time. A second aim is to look at an interaction between FU_time and > group1>group2. > > Thanks a lot in advance, kind regards, > > Sander Verfaillie > > Drs. S.C.J. Verfaillie > > Neuropsycholoog - Onderzoeker > > VU Medical Center Department of Neurology, Alzheimer Center > > Department of Radiology & Nuclear Medicine > > De Boelelaan 1118, 1081 HZ Amsterdam, the Netherlands > > Tel: +31 20 4448527 Room: PK -1 Z 039 > > > > _______________________________________________ > Freesurfer mailing list > Freesurfer@nmr.mgh.harvard.edu > https://mail.nmr.mgh.harvard.edu/mailman/listinfo/freesurfer -- Douglas N. Greve, Ph.D. MGH-NMR Center gr...@nmr.mgh.harvard.edu Phone Number: 617-724-2358 Fax: 617-726-7422 Bugs: surfer.nmr.mgh.harvard.edu/fswiki/BugReporting FileDrop: https://gate.nmr.mgh.harvard.edu/filedrop2 www.nmr.mgh.harvard.edu/facility/filedrop/index.html Outgoing: ftp://surfer.nmr.mgh.harvard.edu/transfer/outgoing/flat/greve/ _______________________________________________ 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. Dit e-mailbericht is alleen bestemd voor de geadresseerde(n). Het kan informatie bevatten die persoonlijk is en niet openbaar mag worden gemaakt krachtens wet- of regelgeving. Gebruik door anderen is niet toegestaan. Indien u niet de geadresseerde(n) bent, wordt u verzocht de verzender hiervan op de hoogte te stellen en het bericht te verwijderen _______________________________________________ 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
