That looks correct. The contrasts for the 2nd example will test whether
the score is equal to 0 or not (and not an interaction between diagnosis
and score). It is not wrong, but I just wanted to make sure you know
what you are testing.
doug
On 12/17/2013 01:50 AM, Rujing Zha wrote:
> Dear all,
> I want to design a group t-test analysis and correlation analysis for
> pial thickness. I have read the PPT of freesurfer.groupanalysis, and I
> wrote a specific design matrix and contrast for my data. However it is
> the first time that I design matrix in fsgdf by freesurfer. I didnot
> confirm whether I wrote is correct. I need someone to help me review it.
> I have two groups, four groups were classified as sex.(Is this
> necessary or correct?)
> Here is my design matrix in fsgdf for 2 group t-test:
> GroupDescriptorFile 1
> Title lh_ttest
> Class con_male
> Class con_female
> Class pat_male
> Class pat_female
> Variables Age edu
> Input subjid1 con_male 19 10
> Input subjid2 con_male 20 20
> Input subjid3 con_male 20 20
> Input subjid4 con_male 19 10
> Input subjid5 con_female 20 20
> Input subjid6 con_female 20 20
> Input subjid7 con_female 19 10
> Input subjid8 pat_male 20 20
> Input subjid9 pat_male 20 20
> Input subjid10 pat_male 19 10
> Input subjid11 pat_female 20 20
> Input subjid12 pat_female 20 20
> DefaultVariable Age
> In this section, I just want to compare the patient group(class 3 and
> 4) and control group(class 1 and 2) in thickness controling the age
> and education by ANCOVA. Does this fsgdf implement ANCOVA?
> Here is my contrast for this:
> 0.5 0.5 -0.5 -0.5 0 0 0 0 0 0 0 0
> Here is my design matrix in fsgdf for partial regression:
> GroupDescriptorFile 1
> Title lh_regression
> Class con_male
> Class con_female
> Class pat_male
> Class pat_female
> Variables Age edu score1 score2
> Input subjid1 con_male 19 10 20 30
> Input subjid2 con_male 20 20 20 30
> Input subjid3 con_male 20 20 20 30
> Input subjid4 con_male 19 10 20 30
> Input subjid5 con_female 20 20 20 30
> Input subjid6 con_female 20 20 20 30
> Input subjid7 con_female 19 10 20 30
> Input subjid8 pat_male 20 20 20 30
> Input subjid9 pat_male 20 20 20 30
> Input subjid10 pat_male 19 10 20 30
> Input subjid11 pat_female 20 20 20 30
> Input subjid12 pat_female 20 20 20 30
> DefaultVariable score1
> In this section, I want to implement partial regression analysis(i.e.
> score1 and score2) by controling the age,edu and sex.
> Here is my contrast for score1:
> 0 0 0 0 0 0 0 0 0 0 0 0 0.25 0.25 0.25 0.25 0 0 0 0
> Here is my contrast for score2:
> 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0.25 0.25 0.25 0.25
> Any reply will be highly appreciated.
> Thanks.
> All the best.
> 2013-12-17
> ------------------------------------------------------------------------
> /Rujing Zha/
>
>
> _______________________________________________
> 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
greve@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.