[pymvpa] ttest: significance level?

[Nick Oosterhof]

On 27 October 2017 at 13:19, Pegah Kassraian Fard <pegahkf at gmail.com> wrote:

> I have a very basic question regarding the provided t-test (
> http://www.pymvpa.org/generated/cmd_ttest.html) which I want to apply to
> my searchlight results:
> Why exactly is there no parameter for the alpha value?
>

Although I did not implement this function myself, my best guess is that it
would have been more work to implement.

However, the output can be set to represent p-values, so it should be
trivial to identify (mask) voxels that pass (or do not pass) a specific
alpha level.



> I guess accordingly, that this t-test is not corrected for multiple
> comparisons?
>

As far is I can see, indeed, it does not.

For multiple comparisons, consider:
http://www.pymvpa.org/generated/mvpa2.algorithms.group_clusterthr.GroupClusterThreshold.html
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.alioth.debian.org/pipermail/pkg-exppsy-pymvpa/attachments/20171027/07eedb3c/attachment.html>