Hey All,
I am sorry to jump into this discussion. I know how to check the slope
difference between groups. I want to ask help from you to confirm that if
difference in thickness in some brain areas arising from (0 0 1 -1)
happens, it means that there is a group * age interaction, right?
Then,
If there is no interaction, then either DODS or DOSS is appropriate.
DOSS will be more powerful and a little more interpretable. If there is
an interaction then DODS must be used, and the interpretation of the
difference between groups becomes more problematic. Eg, if age is the
covariate,
Dear Doug,
I need also to correct for Age and Years of Education by using them as
nuisance covariate. Would you please explain:
Why the covariates should be demeaned?
Is subtracting the mean from each individual the only way of demeaning?
How Qdec regress out the effect of the covariates , linear
On 01/13/2014 11:41 AM, amirhossein manzouri wrote:
Dear Doug,
I need also to correct for Age and Years of Education by using them as
nuisance covariate. Would you please explain:
Why the covariates should be demeaned?
Reduces correlation with the group term and so improves efficiency.
Is
Thanks Doug and how can check if the slopes are different?
On Jan 12, 2014 12:33 AM, Douglas Greve gr...@nmr.mgh.harvard.edu wrote:
Use DODS to test whether the slopes differ between the three groups. If
they do not, then use DOSS.
doug
On 1/11/14 5:03 PM, amirhossein manzouri wrote:
If you have two groups and a single covariate, when you run it with
mri_glmfit create a contrast with [0 0 1 -1]. In QDEC, it will be one of
the default contrasts (something like do the two groups differ in slope?)
doug
On 1/12/14 5:31 AM, amirhossein manzouri wrote:
Thanks Doug and how
Hello all,
I am using Qdec (version5.1) to study cortical thickness differences
between groups having Age as nuisance covariate. I do not have assumption
if the groups are different or not . Using DODS and DOSS gives me
completely different results. We have three groups including 41, 39, and 24
HiAmirhossein, don't use the DOSS feature in QDEC because there is a bug such
that
it does not always do the right thing. Sorry, I sent out an email
about 8mo ago on this, but it is not easy to let people know about a bug
once the bug is out there. If you want to use DOSS, use mri_glmfit
Thanks Doug for the prompt reply. I just want to if DODS is ok to be used
in my case or I should use DOSS?
On Jan 11, 2014 10:56 PM, Douglas Greve gr...@nmr.mgh.harvard.edu wrote:
Hi Amirhossein, don't use the DOSS feature in QDEC because there is a bug
such that
it does not always do the
Use DODS to test whether the slopes differ between the three groups. If
they do not, then use DOSS.
doug
On 1/11/14 5:03 PM, amirhossein manzouri wrote:
Thanks Doug for the prompt reply. I just want to if DODS is ok to be
used in my case or I should use DOSS?
On Jan 11, 2014 10:56 PM,
Hello Douglas,
I did as you suggested and I got the results, but I still have
difficulty understanding how exactly the choice of Design Matrix Type
influences the analysis, so I have several questions:
1. When I look at thickness difference between two groups and choose
age as nuisance
For question #3; #4.
#3
Any good stastistical textbook will be useful. The two that come to mind
are:
(a) Meyers and Wells. Research Design and Statistical A nalysis
(b) Keppel and Wickens. Design and Analysis: A Researcher's Handbook (4th
Edition)
#4
SPM uses the General Linear Model for all
Dear all,
I have two groups of subjects, and I want to see a difference in
thickness between them controlling for age.
I couldn't find any information in the literature on how the subject's
brains in my groups develop with age. Therefore I can't tell whether
thickness as a function of age for
Hi Tanja, you should use DODS and test for a difference between the age
slopes of the groups (ie, an interaction between group and age). If
there are no significant interactions, you should then use DOSS to test
for the difference between thicknesses.
doug
Tetiana Dadakova wrote:
Dear all,
14 matches
Mail list logo
