[FieldTrip] Confidence Intervals for TFR Statistics

[Schoffelen, J.M. (Jan Mathijs)]

Dear Mark,

Yes, there is, and the reason for this is rather mundane. The reason that it isn’t outputted is probably because nobody has ever cared to implement it in the code. Also, it is not clear what you exactly mean with ‘confidence intervals’. If it’s about a CI based on a parametric interpretation of the (mass-univariate) test statistic, there is plenty of matlab code that will allow you to infer this. On the other hand, if it’s about a CI of the (cluster-based) test statistic based on the permutation distribution then this is straightforward to get: just sort the posdistribution and negdistribution fields of the stat output, and look at the relevant quantiles.

Best wishes,

JM

On 6 Jul 2020, at 01:10, Mark Haney <mhaney377 at gmail.com<mailto:mhaney377 at gmail.com>> wrote:

Hello all,

Thank you for the reply earlier on my cfg.clusterstatistics inquiry. I will see if I can upload the changes requested by the community via GitHub.

I am hoping someone could assist me with one more question on this topic: Is there a reason why Fieldtrip doesn't output confidence intervals for TFR data in the "stat" output?

Thanks again, everyone!

Mark
_______________________________________________
fieldtrip mailing list
https://mailman.science.ru.nl/mailman/listinfo/fieldtrip
https://doi.org/10.1371/journal.pcbi.1002202

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.science.ru.nl/pipermail/fieldtrip/attachments/20200706/1b756272/attachment.htm>