The value = (CU cortisol low - CU cortisol high) - (CI cortisol low - CI
cortisol high), so whatever that sign means. BTW, you are supposed to
decide the sign for a singed test *before* you look at your data.
On 2/18/2022 2:39 PM, Laura Willers de Souza wrote:
External Email - Use Caution
Got it!
The 4 groups I'm testing are: CU cortisol low; CU cortisol high; CI
cortisol low; CI cortisol high.
So if I found a significant cluster for this contrast, can I interpret
that the cortical thickness of this region of the cluster is affected
by both the diagnosis and cortisol levels?
In this case I made the correction of multiple comparisons with
positive direction. That means that the worse the diagnosis and the
cortisol levels (CI cortisol high) the more the cortical thickness of
this region of the cluster will be affected, or to draw this
conclusion would I need the results of the other contrasts as well?
Thanks so much for all the help!
Best,
*Laura Willers de Souza *
Master Student in Biochemistry
Zimmer Lab - Federal University of Rio Grande do Sul
- Porto Alegre/RS - Brazil
------------------------------------------------------------------------
*De:* Douglas N. Greve <dgr...@mgh.harvard.edu>
*Enviado:* quinta-feira, 17 de fevereiro de 2022 20:25
*Para:* Laura Willers de Souza <laura.w.deso...@hotmail.com>
*Assunto:* Re: [Freesurfer] Question glm analysis g4v0
No, that was only for interactions between the covariates and the groups
On 2/17/2022 10:05 AM, Laura Willers de Souza wrote:
External Email - Use Caution
Hello FreeSurfer Developers,
I am performing a GLM analysis to assess cortical thickness between 4
groups, without any covariates. I followed exactly what is on the
wiki *MailScanner has detected a possible fraud attempt from
"secure-web.cisco.com" claiming to be*
https://surfer.nmr.mgh.harvard.edu/fswiki/Fsgdf4G0V
<https://secure-web.cisco.com/1VuhMA49mKmIDKH_rGPy4c67MdbjL6bNv2i_WwNDwvMA5-MXr4tsqwQ6IStvSqNebMH5W36rEr0USbcPY6VSldSWInkjYUYATJN4-hScZf_-OvN7DjNFuD1LqLQPslKlEsRs2i5Frm5hCanY-mdYmoXDgRz99okbQHufSeXw7dl5Kao9r4PrXqZg1WBJq3pdh84vjS8osSMXbvqa3uhBkUhrQKMdQVsoDKPcfYvWBgQuvit_2zj-tuv-KuUpx8AwguemupjLL0D3erYK1Zx04S5eNVbsno35BFPDcDUyqYAvbdgwvH_RznbsqiWfBzdzKk5pv1hKHnRAHmRmAEopQBA/https%3A%2F%2Fsurfer.nmr.mgh.harvard.edu%2Ffswiki%2FFsgdf4G0V>
In a previous analysis (*MailScanner has detected a possible fraud
attempt from "secure-web.cisco.com" claiming to be*
https://www.mail-archive.com/freesurfer@nmr.mgh.harvard.edu/msg71673.html
<https://secure-web.cisco.com/1qw-8Oc7vg0Tc3_ilXhnADw1_lWmUuUCQVr-MNNAiNRRR1O7MdJfPrEZTHnMCCdhrDYe2IGToziozmFZH9DmDjotHxZ13mSQ0meaYg54YZ3W49R5GmOOmv4pxtTQu6pCj6_X-TzVX_idBkKXYowz5SJjSSCz5SIX10hNl02tyfJRj7faXxmJCmpUARlF_WNVwe6Sh09yFRd_F6a9Q6mEUCZ0SjFdtnVii54is5AIDIJzLw_YXEx4Q_wEUnHtJoDca8nRl3HFIAZcmhGZIYKj_HK_8kUl0X_hKIh23Y9M1XOPEtCnVm3dt3tNuF7UX49wVzWEzktO7A9zzUhoAHRayaA/https%3A%2F%2Fwww.mail-archive.com%2Ffreesurfer%40nmr.mgh.harvard.edu%2Fmsg71673.html>),
Dr Douglas had told me that before any analysis I should test whether
the interaction is significant or not.
I would like to know if this also applies to this case, the
interaction being tested by contrast number 7 of the wiki.
Thanks in advance!
Best,
*Laura Willers de Souza *
Master Student in Biochemistry
Zimmer Lab - Federal University of Rio Grande do Sul
- Porto Alegre/RS - Brazil
_______________________________________________
Freesurfer mailing list
Freesurfer@nmr.mgh.harvard.edu <mailto:Freesurfer@nmr.mgh.harvard.edu>
https://mail.nmr.mgh.harvard.edu/mailman/listinfo/freesurfer
<https://secure-web.cisco.com/1zu97k27XDcB0udYaGQREHk5Q8tG-qfZ9sx9jUVH-pKJSMRvPDJ9GZh8ZGCyRHtW8rTz4BQ-P-vZkyKy1IizEnsrtTQ0Z7iQbeDBxkDIFt7i3Ud1M4Vvi9klyxDSRoWGj_a8ShXN7LCQdhSCzEbMYWIF14Nn7hSNsgxyo80yyW0q_Nlo0uV5Rpy156I7G3jEX7yGwJJ6NFBaMtvqRS97fV2d_yC6EvF458xurV3AEdAV0NmNvjyrFmDht2h6lzvYJaikVgCNZ97ch8oXolnttgCI02PqdW2-GU0X4LH4YtvlbMVZHmWlLkSvejvouA4_w/https%3A%2F%2Fmail.nmr.mgh.harvard.edu%2Fmailman%2Flistinfo%2Ffreesurfer>
_______________________________________________
Freesurfer mailing list
Freesurfer@nmr.mgh.harvard.edu
https://mail.nmr.mgh.harvard.edu/mailman/listinfo/freesurfer