Hi everyone,
I am performing a TBSS analysis on two groups of subjects and I have to covariate for age but I have some doubts regarding the design of the matrix used for the statistical analysis.
First of all, what's the difference between using one single group and using two different groups?
Then how do the EVs and the contrasts change in the two cases?
I will give you an example to clarify my question.
If I use une a single group the design should be
EV1 EV2 EV3(AGE) EV4(AGE2) ?
1 1 0
1 1 0
.
.
.
1 0 1
1 0 1
1 0 1
in this case should I use two different EVs one for the age of the first group and one for the second or a single one?
How do I have to contruct this contrasts?
group1 vs group2
group1 vs group2
positive correletion with age
negative correletion with age
On the other side if I use two groups the design will be
EV1 EV2 EV3(AGE) EV4(AGE2)
1 1 0
1 1 0
.
.
.
2 0 1
2 0 1
2 0 1
The same questions as above: should I use two different EVs one for the age of the first group and one for the second or a single one? How do I have to contruct the contrasts?
And which of the two design is better or wich is the difference?
I hope my question is clear...
Thank you very much
Lucia
|