Hi - no there is no problem with having different group sizes here, everything should be accurate. Cheers. On 29 Mar 2009, at 02:27, Yi-Shin Sheu wrote: > Dear FSL experts, > > I am doing a two-sample t-test group comparison using 20 patients > and 60 > controls, and would like to use randomise to do permutation test as to > derived corrected p value statistical maps. > > I read on the FSL official website for randomise, it stated " ..... > For > large sample sizes, with 50-100 or more degrees of freedom, the P- > values > should be highly accurate. When the sample size is low and there are > many > nuisance regressors, accuracy could be a problem." > > My group size is large (N=80), however, it consists of relatively > small > number (N=20) of patient and a relatively large number (N=60) of > control. > Will the discrepancy in group size lead to serious statistical > problems? > Will that be a better idea if I only pick those controls who are > best match > to patients, to reduce the groups size differences and obviate the > need to > use nuisance covariates. > > Thank you in advance for your help. > > Best, > > Yi-Shin > --------------------------------------------------------------------------- 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 ---------------------------------------------------------------------------