[Eeglablist] LIMO EEG contrast issues

Dr Cyril, Pernet wamcyril at gmail.com
Fri Apr 18 04:54:52 PDT 2025


Hi Ozger,

you are not wrong, there is not documentation for repeated measures + 
covariates because it is not supported. Not sure about the 'bug' since 
an ANCOVA would not allow to do what you want. One way around it is to 
regress the covariates and then run the repeated measure on the 
residuals of the regression model and hack the degrees of freedom (ie -2).

cyril




> Hello,
>
> I am using LIMO to analyze a 2 x 2 design with a repeated measures ANOVA. I was able to get it to work and see all the results as intended. I am now trying to add two continuous variables to the same design and I am somewhat lost on how to proceed. I understand an ANCOVA does not work with this per the GUI message, which suggests running contrasts and covarying on them. At no point in the analyses the con files were generated, so I went to use the contrast manager to create contrasts. This has been very buggy for me. It seems the contrast pipeline created was not able to access the C variable that housed the [1 -1] array because it was in a nested C structure. I modified the source code of limo_batch to add another .C to the opt.C (line 441), and this actually does result in proper contrast files, but then the pipeline locks at some point and the remaining contrasts are not generated.
>
> Is this a bug or am I missing something? Perhaps there is a better way to covary in this design?
>
> Thank you,
>
> Can Ozger
> PhD Student
> Neurosciences Graduate Program
> University of California San Diego
> _______________________________________________
> To unsubscribe, send an empty email to eeglablist-unsubscribe at sccn.ucsd.edu or visit https://sccn.ucsd.edu/mailman/listinfo/eeglablist .

-- 
Dr Cyril Pernet, PhD, OHBM fellow, SSI fellow
Neurobiology Research Unit,
Building 8057, Blegdamsvej 9
Copenhagen University Hospital, Rigshospitalet
DK-2100 Copenhagen, Denmark

wamcyril at gmail.com
https://urldefense.com/v3/__https://zcal.co/cpernet__;!!Mih3wA!Fw9niXgJo6nFN55Jj3seD9dC8r4fnV7wH5yybBpdIofSxS01wvMz4-FNWVy6LZbijaRwooTTpY77nDuYhOIxJw$ 
https://urldefense.com/v3/__https://cpernet.github.io/__;!!Mih3wA!Fw9niXgJo6nFN55Jj3seD9dC8r4fnV7wH5yybBpdIofSxS01wvMz4-FNWVy6LZbijaRwooTTpY77nDtzgawh4w$ 
https://urldefense.com/v3/__https://orcid.org/0000-0003-4010-4632__;!!Mih3wA!Fw9niXgJo6nFN55Jj3seD9dC8r4fnV7wH5yybBpdIofSxS01wvMz4-FNWVy6LZbijaRwooTTpY77nDswuK8QPQ$ 



More information about the eeglablist mailing list