Hi again,
> when i compare
> control (N) with other groups like C,B and E i expect
> differences because these are ALS patients too who are
> categorized into different subtypes based on their different
> clinical symptoms. Do i need to reverse the contrast
> to see differences between N-C, N-B and N-E or the my
> contrast matrix is correct but there is no significant
> difference between control and these subtypes.
No, your contrasts are fine though you could always check is something is going on in the opposite direction (sometimes the most interesting results come from the least expected contrast)...
If they are subtypes of ALS, then I guess your n might be smaller than for the D group, which might explain why it doesn't reach significance... You should have a look at your uncorrected p-values and unthresholded corrected p-values to see if you're anywhere close to getting something significant. Have you tried the FDR and TFCE correction for multiple comparisons?
Cheers,
Gwenaelle
__________________________________________________
Do You Yahoo!?
En finir avec le spam? Yahoo! Mail vous offre la meilleure protection possible contre les messages non sollicités
http://mail.yahoo.fr Yahoo! Mail
|