[Eeglablist] Reg_p value extraction

Delorme, Arnaud adelorme at ucsd.edu
Tue Oct 22 16:10:13 PDT 2019


Dear Yadav,

The type of information that can be returned depend on your design. In your case, it seems you did everything right. My guess is that in the study design you were using (and you can have several in a given STUDY), there were several conditions but not multiple groups. As a consequence EEGLAB could not compute statistics across groups and the interactions. I would double check that the current design contain indeed several groups (try plotting them for example). You can change the current design in the EEGLAB graphical interface or by typing

STUDY.currentdesign = 1; % if you want to select the first design

Best wishes,

Arno

> On Oct 19, 2019, at 3:30 AM, Saraswati Yadav <saraswati.y at cbcs.ac.in> wrote:
> 
> Dear All,
> I am having error in extracting the p value from specdata after creating a
> STUDY and plotting the topoplot. I have 3 groups in my study with resting
> EEG data of 5 mins recorded in 128 channel EGI system.
> Writing the following is not helping me for extracting p values from 5
> channels.
> STUDY = pop_statparams(STUDY, 'condstats', 'on','groupstats','on');
> [STUDY specdata specfreqs pgroup pcond pinter] =
> std_specplot(STUDY,ALLEEG,'channels',{'E1', 'E2' ,'E3' ,'E4' ,'E5'});
> 
> This gives us five p values in pcond for 5 channels I think. But no values
> in pgroup and pinter. What I am interested in is extracting the p values
> for Group and channel interaction using 2 way ANOVA design Where IV1 to be
> Channels (5 levels) and IV2 as Groups (i.e 3 levels)
> 
> 
> Thanking in advance.
> 
> 
> 
> -- 
> Dr.Saraswati Yadav
> Post Doctoral Fellow
> Centre of Behavioural and Cognitive Sciences
> University of Allahabad
> India
> _______________________________________________
> 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



More information about the eeglablist mailing list