Displaying 2 results from an estimated 2 matches for "affimetrix".
2004 Dec 20
2
problems with limma
...409.8391 6.414966 0.4192042 -4.593307
10960 -511.4711 -5.469247 0.9652171 -4.593435
> #
>
So the results I get from just pairwise comparisons are very significant, but
when I try the Anova way, the significance completely dissapears.
Am I doing something completely wrong?
This is data from Affimetrix mouse chips.
Thanks for any help
Heberto Ghezzo
Ph.D.
Meakins-Christie Labs
McGill University
Montreal - Canada
2004 Dec 21
0
Fwd: problems with limma
...ook at your data and do some quality assessment. At very least you
probably need to log-transform.
Your 4-group approach should give the same M-values as the 2-group approach, but the standard
errors and t-statistics will change because your error estimates change.
Gordon
> This is data from Affimetrix mouse chips.
> Thanks for any help
> Heberto Ghezzo
> Ph.D.
> Meakins-Christie Labs
> McGill University
> Montreal - Canada