Print

Print


Hi - if you only have a very small number of inputs to mixed effects it cannot estimate the variance well. You will probably need to use fixed effects.
Cheers.




On 14 Jun 2011, at 19:36, Dixit, Sachin wrote:

Dear FSL experts,
I am trying to do higher level Group analysis, which is sort of Lev4 analysis where I am interested in Dosage Interactions. Lev 3 I did seperate analysis for each dosages with each task and did both Fix Effect and Mix Effect. Now to see the interaction of dosages I am combining the result of previous level 3, that is my input are Task1_Dosage1_ME/FE + Task1_Dosage2_ME/FE + Task3_Dosage3_ME/FE, where ME is for Mix Effect and FE: Fix Effect
The above steps worked for FE but for ME the log file under higher level stats shows me the following error:
An exception has been thrown
Nevs >= ntpts, Singular matrix.Trace: Gsmanager::flame_stage1;Gsmanager::run
And eventually the program breaks at Post-stats
 
Please advise.
 
Sachin
 


The materials in this message are private and may contain Protected Healthcare Information or other information of a sensitive nature. If you are not the intended recipient, be advised that any unauthorized use, disclosure, copying or the taking of any action in reliance on the contents of this information is strictly prohibited. If you have received this email in error, please immediately notify the sender via telephone or return mail.


---------------------------------------------------------------------------
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
---------------------------------------------------------------------------