I have a clarifying question about fsgd file format.
We have 40 participants, and a large battery of individual difference
measures (egg., vocabulary, phonological skill, etc.)
We applied a PCA to the battery and found 4 components, corresponding to
WMC, processing speed, comprehension ability, and phonological ability.
We tested for main effects of each of these on thickness, area, and volume
via QDEC.
However, we also want to check for interactions - and since this is
essentially 4 continuous factors, this is not QDEC-able (at least, it does
not appear to be). A nuisance variable (e.g., mean thickness) is also
present.
Nregressors = Nclasses*(Nvariables+1) = 1*((4 components + 1 nuisance) +1)
= 1*(5+1) = 6
Null contrast is
1 0 0 0 0 0
Main effect, e.g., of the working memory component (#1) is
0 1 0 0 0 0
Main effect, e.g., of the WM component modulated by the nuisance variable is
0 1 0 0 0 1
So the format to examine possible interactions, e.g., component 1 and
component 2 interact to affect thickness, is
0 1 1 0 0 0
And with the nuisance variable
0 1 1 0 0 1
Do we have this right?
THANKS!!
Clint
--
I remain...
Clinton L. Johns, Ph.D.
Research Scientist, Haskins Laboratories
300 George Street
New Haven CT 06511
speech: 203-865-6163 x240
fax: 203-865-8963
net: johns(a)haskins.yale.edu