[Eeglablist] ERSP stats EEGLAB STUDY

[Makoto Miyakoshi]

Dear Radha,

For the BEFORE/AFTER comparison, I assume the statistical design is a
paired t-test.
In that case, EEGLAB function statcond() use paired t-test by default as
you can see below (taken from statcond help)

    'paired'   = ['on'|'off'] pair the data array {default: 'on' unless
                 the last dimension of data array is of different lengths}.

About one-tailed or two-tailed, statcond() says it uses two-tailed test for
t-test as you can see below.

    'tail'     = ['one'|'two'] run one-tailed (F-test) or two tailed
                 (T-test). This option is only relevant when using the
                 'surrog' input. Otherwise it is ignored.

Makoto


On Wed, Jul 6, 2022 at 8:27 AM Radha Kumari (PGR) <
2375059K at student.gla.ac.uk> wrote:

> Hello,
>
> I really hope someone can help me on this one. I am struggling to
> determine the statistical tests performed in EEGLAB STUDY to compare ERSP
> data in a BEFORE and AFTER design. I really need to know what EEGLAB is
> doing so that I know what to report in the statistics section of my paper.
> I have tried with no luck to reproduce EEGLAB STUDY statistical results.
> Does anyone know the type of statistical test and any data transformation
> that EEGLAB STUDY does to compare ERSP data in a BEFORE and AFTER design?
> Is it a one-sided or two-sided test? Also let me know if you know the
> relevant part of EEGLAB code.
>
> Radha
> _______________________________________________
> 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
>