to run t-test without trimmed means - alpha level missing in limo_random_robust[BUG]

LIMO-EEG-Toolbox / limo_tools

Hierarchical Linear Modelling for MEEG data

https://limo-eeg-toolbox.github.io/limo_meeg/

Other

58 stars 28 forks source link

to run t-test without trimmed means - alpha level missing in limo_random_robust[BUG] #185

Closed mariajribeiro closed 6 months ago

mariajribeiro commented 6 months ago

limo_random_robust line 400

[~,~,~,~,~,t{b},p{b}]=limo_ttest(2,Y1(1,:,boot_table1{channel}(:,b)),Y2(1,:,boot_table2{channel}(:,b)));

it crashes in limo_ttest because variable alphav is missing. fixed by adding extra input variable with alpha level.

CPernet commented 6 months ago

Hi Maria, ok will do - can you tell me why you use LIMO.design.method ='Mean' rather then the default?

mariajribeiro commented 6 months ago

Hi. I am trying this because there was an obvious difference in means and I was checking if the lack of significant clusters was because of the trimmed means. Obviously, these differences not very "robust" :(

CPernet commented 6 months ago

fixed in 3.4 and master, thx