Hi - for a two-group test set the number of EVs to 2 (you need an EV for
each group that you want to model) and for each row in the model put a
single 1ยง in the appropriate column (EV). The "Group" membership on the
left is not part of the model - it's specifying which group each row
(person etc) is in for the purposes of variance estimation - so this
should be 1,2, etc.
Cheers, Steve.
On Fri, 2 Sep 2005, Jodi Edwards wrote:
> Hello,
> I am doing an unpaired two-group t-test and noticed that the example given on the website allows
> you to set the group number to two. This option does not even come up on our software (ie: there is
> no number of groups menu in the model setup). There is a group EV and I did set half of the group
> to number two, however, when I look at the report.log, the parameters in the higher order stats
> section specifiy that the ngrps=1. Is there a way to ensure that the analysis is between groups?
> Thanks very much!
> Jodi Edwards
> Seaman Family MR Research Centre
> University of Calgary
>
--
Stephen M. Smith DPhil
Associate Director, FMRIB and Analysis Research Coordinator
Oxford University Centre for Functional MRI of the Brain
John Radcliffe Hospital, Headington, Oxford OX3 9DU, UK
+44 (0) 1865 222726 (fax 222717)
[log in to unmask] http://www.fmrib.ox.ac.uk/~steve
|