yes, they are, though you don't need to do the positive and negative
contrasts because the sign is preserved
doug
On 02/20/2014 12:47 AM, charujing123 wrote:
> Hi FS experts and users,
> I am trying to implement independent sample t-test and correlation
> analysis.
> Here is my fsgdf design:
> -----------------------------
> GroupDescriptorFile 1
> Title lh_ttest
> Class CON_IA
> Class PAT_IA
> Variables score1 score2
> Input CON_IA01 CON_IA 0 0
> Input CON_IA03 CON_IA 0 0
> Input CON_IA05 CON_IA 0 0
> Input CON_IA06 CON_IA 0 0
> Input CON_IA07 CON_IA 3 7
> Input CON_IA09 CON_IA 0 0
> Input CON_IA14 CON_IA 0 0
> Input CON_IA15 CON_IA 0 0
> Input CON_IA16 CON_IA 7 12
> Input CON_IA19 CON_IA 6 15
> Input CON_IA24 CON_IA 6 11
> Input CON_IA27 CON_IA 3 3
> Input CON_IA32 CON_IA 7 21
> Input CON_IA33 CON_IA 7 21
> Input CON_IA35 CON_IA 0 0
> Input CON_IA38 CON_IA 7 15
> Input CON_IA39 CON_IA 2 3
> Input CON_IA40 CON_IA 6 8
> Input CON_IA41 CON_IA 2 4
> Input PAT_IA01 PAT_IA 8 13
> Input PAT_IA02 PAT_IA 9 38
> Input PAT_IA03 PAT_IA 9 33
> Input PAT_IA04 PAT_IA 9 27
> Input PAT_IA06 PAT_IA 9 26
> Input PAT_IA08 PAT_IA 8 16
> Input PAT_IA09 PAT_IA 9 33
> Input PAT_IA16 PAT_IA 9 35
> Input PAT_IA18 PAT_IA 9 39
> Input PAT_IA21 PAT_IA 9 32
> Input PAT_IA22 PAT_IA 9 31
> Input PAT_IA23 PAT_IA 9 35
> Input PAT_IA24 PAT_IA 9 40
> Input PAT_IA25 PAT_IA 9 29
> Input PAT_IA27 PAT_IA 9 30
> Input PAT_IA29 PAT_IA 9 30
> Input PAT_IA30 PAT_IA 8 32
> Input PAT_IA33 PAT_IA 9 13
> Input PAT_IA34 PAT_IA 9 21
> ------------------------------------------------
> Contrasts for independent sample t-test:
> 1,CON_IA>PAT_IA:1 -1 0 0 0 0
> 2,PAT_IA>CON_IA:-1 1 0 0 0 0
> Contrasts for correlation analysis:
> 1,possitive correlation analysis between pial thickness and score1:0 0
> 0.5 0.5 0 0
> 2,negtive correlation analysis between pial thickness and score1:0 0
> -0.5 -0.5 0 0
> 3,positive correlation analysis between pial thickness and score2:0 0
> 0 0 0.5 0.5
> 4,negtive correlation analysis between pial thickness and score2:0 0 0
> 0 -0.5 -0.5
> Are my designs appropriate?
> If I want to implement regression analysis(i.e. dependent variable is
> thickness and independent variables are score1 and score2), how to
> design my contrast?
> Thanks.
> All the best.
> Rujing Zha
> 2014-02-20
> ------------------------------------------------------------------------
> charujing123
>
>
> _______________________________________________
> Freesurfer mailing list
--
Douglas N. Greve, Ph.D.
MGH-NMR Center
Phone Number: 617-724-2358
Fax: 617-726-7422
Bugs: surfer.nmr.mgh.harvard.edu/fswiki/BugReporting
_______________________________________________
Freesurfer mailing list
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
but does not contain patient information, please contact the sender and properly
dispose of the e-mail.