Sounds like you need an F-test, eg, create a contrast like 1 1 -1 -1  0  0 0 0 0 0 0 0 1 1  0  0 -1 -1 0 0 0 0 0 0

This tests the null hypothesis that p1==p2==control

On 11/07/2018 10:11 AM, 13181786167 wrote:

External Email - Use Caution

Thanks for your reply. Using the first one, We can obtain the sig.mgh among 3 groups. If I want to obtain the results simultaneously between patient 1 and 2, patient 1 and control, patient 2 and control. What should I do.

Sincerely, Zheng

郑凤莲 邮箱：13181786167@163.com

https://maas.mail.163.com/dashi-web-extend/html/proSignature.html?iconUrl=http%3A%2F%2Fmail-online.nosdn.127.net%2F045c9f9c64b625832c45daba6225f5de.jpg&name=%E9%83%91%E5%87%A4%E8%8E%B2&uid=13181786167%40163.com&ftlId=1&items=%5B%22%E9%82%AE%E7%AE%B1%EF%BC%9A13181786167%40163.com%22%5D

签名由 网易邮箱大师 https://mail.163.com/dashi/dlpro.html?from=mail88 定制

    On 11/07/2018 22:57, Greve, Douglas N.,Ph.D.
    <mailto:DGREVE@mgh.harvard.edu> wrote:
    Use the first one. Not sure what you mean by your multiple
    comparisons
    question

    On 11/01/2018 11:20 PM, 郑凤莲 wrote:
    >
    >         External Email - Use Caution
    >
    > Hi experts,
    >
    > I am using FS 6.0 for analyzing the cortical thickness
    difference
    > between 3 groups: patient1, patient2 and control. In DODS
    model, I
    > need to creat 2 files, FSDG and mtx file. And we have
    3 variables:
    > age, gender and cortical thickness.
    > 1. The FSDG file is:
    > GroupDescriptorFile 1
    > Title Tutorial
    > Class patient1-male
    > Class patient1-female
    > Class patient2-male
    > Class patient2-female
    > Class control-male
    > Class control-female
    > Variables                                 age
    > Input subject1 patient1-female 20
    > Input subject2 patient1-male    33
    > Input subject3 patient2-female 40
    > Input subject4 patient2-male    50
    > Input subject5 control-male    30
    > Input subject6 control-female 35
    > And there is another way:
    > GroupDescriptorFile 1
    > Title Tutorial
    > Class patient1
    > Class patient2
    > Class control
    > Variables                     sex age
    > Input subject1 patient1 1   20
    > Input subject2 patient1 2   33
    > Input subject3 patient2 1   40
    > Input subject4 patient2 2   50
    > Input subject5 control   2   30
    > Input subject6 control   1   35
    > What I want to confirm is that if I want to adjust for sex
    and age,
    > which one is right?
    > Another question is that is there any way to get the multiple
    > comparisons between groups simultaneously?
    > I am looking forward to your reply. Thanks very much.
    >
    > Sincerely,
    > Zheng
    >
    >
    >
    >
    > _______________________________________________
    > 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