 |
 |
Ciara, You can't test the main effect of group using a flexible factorial design. The error term is incorrect. To test the main effect of group, you need to create an average of the 8 conditions and then set up another model with 3 groups. The contrast (an F) will be: 1 -1 0 0 1 -1 On Fri, Jun 12, 2009 at 5:51 AM, Ciara McCabe <[log in to unmask]>wrote: > Dear Karl > > I hope you don't mind me writing to you but I'm confused about the best way > to analyze my dataset and would really appreciate your advice. > I have 3 groups 2 drugs 1 placebo and 8 conditions. 15 subjects per group. > I (with the help of Cyril and Jan Glascher) have set up a flexible > factorial design in spm5 with subjects, group and condition as factors. > > I haven't been able to figure out how to do a main effect of group (with > the 3 groups in) I have attached the design matrix to show what I have done. > > Also I have now done comparisons between groups for each condition and have > great results with a threshold of 0.001 unc and clusters corrected at 0.001 > etc > so that is comparing drug 1 with placebo > then drug2 with placebo > and I compare drug 1 with drug 2 > > but is this the best way to do it? how do I really compare the 3 groups ? > > also to extract the bold signal change i would like to do it for the > clusters and have tried MARSbar but I'm getting errors > perhaps because its a flex design not sure > is there another way to extract the bold from perhaps a ROI identified from > a condition activated by ALL-subjects (n=45) > so I have identified a cluster how do I analyse just this region between > groups in spm5 > or could i extract the data and then analyse this data in spss is this > valid? would it get around the problem of comparing the 3 groups directly? > > Thanks so much hope it made sense :) > > Thanks > Ciara > > > > Dr Ciara McCabe > Neurosciences Building > Department of Psychiatry > Warneford Hospital > University of Oxford > Warneford Lane > Oxford > > Tel:01865 223778 > mob:07966035631 > E:[log in to unmask] <[log in to unmask]> > > http://www.psychiatry.ox.ac.uk/research/researchunits/perl/perlmembers/ciaramccabe/ > -- Best Regards, Donald McLaren ===================== D.G. McLaren University of Wisconsin - Madison Neuroscience Training Program Office: (608) 265-9672 Lab: (608) 256-1901 ext 12914 ===================== This e-mail contains CONFIDENTIAL INFORMATION which may contain PROTECTED HEALTHCARE INFORMATION and may also be LEGALLY PRIVILEGED and which is intended only for the use of the individual or entity named above. If the reader of the e-mail is not the intended recipient or the employee or agent responsible for delivering it to the intended recipient, you are hereby notified that you are in possession of confidential and privileged information. Any unauthorized use, disclosure, copying or the taking of any action in reliance on the contents of this information is strictly prohibited and may be unlawful. If you have received this e-mail unintentionally, please immediately notify the sender via telephone at (608) 265-9672 or email.