[Eeglablist] Troubleshooting Paired Sample T-Test Error in LIMO with EEGLAB v2023.1

[Cedric Cannard]

Dear Su,

My intuition reading this is that you didn't perform the bootstrap. You need to check the little box when you launch the paired t-test. You need the bootstrap to estimate H0 (the null hypothesis). 

Also, TFCE-correction takes longer but is preferable as it is threshold-free. I'd recommend performing it too.

Cheers,

Cedric



------- Original Message -------
On Wednesday, October 25th, 2023 at 10:31 PM, 봉수현 via eeglablist <eeglablist at sccn.ucsd.edu> wrote:


> Hello? I am having difficulty performing a simple Paired sample t-test using LIMO, so I am reaching out via email.
> 
> It's an error that I can't understand based on my basic statistical knowledge.
> 
> First of all, I have a total of 6 stimulus conditions, and I want to compare two of these conditions. To do this, I set only these two conditions as Categorical variables in the study design and entered the following in LIMO: Estimate Model parameters -> ERP, WLS, 'timelim' [-200 650'] and clicked OK. After the 1st level analysis was completed, I chose the Paired t-test in the 2nd level analysis and entered the beta file. The calculations went well, and for Plotting, I clicked on Plot and selected Level2 -> paired_ttest/paired_samples_ttest_parameter_1_2.mat.
> 
> At this point, the Uncorrected threshold appears fine, but when I select Cluster correction to correct it, I get the message 'cluster correction failure' and 'H0\H0_paired_samples_ttest_parameter_1_2.mat not found.' In my H0 folder, I only have the boot_table.mat and H0_paired_samples_ttest_parameter_2.mat files.
> 
> Did I make a mistake somewhere? I am using EEGLAB v2023.1 and LIMO 4.0.
> 
> Would you like further assistance with your issue?
> 
> Best,
> 
> Su Hyun Bong
> 
> 봉수현 Su Hyun Bong의과학대학원-박사과정34141 대전광역시 유성구 대학로 291 한국과학기술원(KAIST)Tel 042-350-4285 Mobile 010-9891-8020 Email  npdrbong at kaist.ac.kr mailto:npdrbong at kaist.ac.kr
> 
> 
> _______________________________________________
> 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