[Eeglablist] About contrasts and simple effects in LIMO

[Dr Cyril, Pernet]

Hi Marina,

what model have you set up? if you have 4 columns, that would be a N-way 
ANOVA which does not do within-subjects. I recommend a repeated measure 
T^2 and the model should show only 2 columns for the within-subject 
factor, while group is coded separately. (like eg here 
https://urldefense.com/v3/__https://github.com/LIMO-EEG-Toolbox/limo_meeg/wiki/9.-Between-subjects**B-ANOVAs-with-repeated-factors__;4oCZ!!Mih3wA!AwB90Mm5FFA4KGcnSIiybgsVkqymsLtJa3akgObBbSxvkzrzTWRiqPpPu-E8ExVO1lN83HHcAVOUsmuIUdJnPA$  )

You can follow-up by paired t tests for each group (if using STUDY txt 
files of betas parameters per group are saved) and then 2 sample t-tests 
on each betas (in all likelihood you need to create txt files for this 
one). Contrasts are useful in thins context to pull multiple conditions 
but since you only have 2 it won't help.

Let me know if you need more help

Best

Cyril


> Hello everybody,
>
> I write this email because I would like to calculate simple effects with LIMO. I’ve already tried with the “contrasts” option. However, the graphs I get don’t make a lot of sense to me, which makes me think I must be doing something wrong.
>
> I have a 2x2 design. Specifically, 2 different groups of people (between-factor) and 2 different conditions for all subjects (within-factor). As I’ve found the interaction is significant, I would like to check the simple effects. Specially: (a) the simple effect of condition in Group 1, (b) the simple effect of condition in Group 2, (c) the simple effect of Group in Condition1, and (d) the simple effect of Group in Condition2. How should I write this information to LIMO? I’ve already tried this. For the simple effect of:
> a) Condition in Group 1:	1 0 -1 0
> b) Condition in Group 2:	0 1 0 -1
> c) Group in Condition1:         1 -1 0 0
> d) Group in Condition2:	        0 0 1 -1
>
> Nevertheless, when trying to calculate (b) and (d), the program fails to respond. In addition, the graphs obtained for (c) are the same as the ones obtained for the interaction and the main effect of group, which makes me a bit skeptical about these analyses.
>
> It would be very appreciated if anyone could give some hints or advices in this regard.
>
> Yours faithfully,
> Marina Pi-Ruano
>
>
> _______________________________________________
> Eeglablist page: http://sccn.ucsd.edu/eeglab/eeglabmail.html
> To unsubscribe, send an empty email to eeglablist-unsubscribe at sccn.ucsd.edu
> For digest mode, send an email with the subject "set digest mime" to eeglablist-request at sccn.ucsd.edu