On Tue, 24 Oct 2006 00:09:19 -0400, Darren Gitelman
<[log in to unmask]> wrote:
>>
>>Second, when setting up a PPI in SPM, what's the difference
>>between not including a particular task from my model, or
>>including it with a weight of 0?
>
>None. Setting the weight to 0 effectively removes it from the model.
Could someone clarify this last issue to me please? I have done a PPI
analysis in a blocked design. When I look at the design matrix of the
analysis (with three predictors: one psychological, one physiological and
one interaction), the scans relating to blocks of tasks that I do not want
in the interaction are still there. I thought that in this way they are
included in the model and hence, affect the interaction. Or am I missing
something obvious?
Kind regards,
Seppe Santens
|