Hi,
You need the demean option if your model does NOT include non-zero-
mean EVs - ie if all EVs have been demeaned. If you do have EVs that
model the mean, then you should not demean your data with the -D option.
The difference between 5000 and 1000 will not be very high - you will
just get slightly more accurate p-values with more permutations.
Cheers.
On 14 Nov 2008, at 00:19, India Bohanna wrote:
> Hi. I would like to know why the -D (demean) option is recommended
> when running
> randomise on a TBSS analysis? I have run randomise without using -D
> and am wondering if
> I need to re-run the analysis. Also, what difference (if any) should
> I expect to see when
> using -n 5000 compared to -n 1000? I understand that there may be
> some difference in the
> results, but is this difference likely to be big? Thanks, India.
---------------------------------------------------------------------------
Stephen M. Smith, Professor of Biomedical Engineering
Associate Director, Oxford University FMRIB Centre
FMRIB, JR Hospital, Headington, Oxford OX3 9DU, UK
+44 (0) 1865 222726 (fax 222717)
[log in to unmask] http://www.fmrib.ox.ac.uk/~steve
---------------------------------------------------------------------------
|