[FieldTrip] ft_timelockstatistics tails

[Mathis Kaiser]

Hi Patrick,

unless you have specified cfg.correcttail = 'prob', you are correct in
assuming you have to double the cluster-level p-values for a two-tailed
test.

See
http://www.fieldtriptoolbox.org/faq/why_should_i_use_the_cfg.correcttail_option_when_using_statistics_montecarlo/

Best,
Mathis

On 23.04.19 17:18, psdwyer at ucdavis.edu wrote:
> Hello,
> 
> I was wondering if I could ask a clarification question about the
> correct interpretation of the outputs of Fieldtrip’s
> ft_timelockstatistics function?
> 
> Online, it says:
> 
> “We use cfg.alpha to control the false alarm rate of the permutation
> test (the probability of falsely rejecting the null hypothesis). The
> value of cfg.alpha determines the critical values with which we must
> compare the test statistic (i.e., the maximum and the minimum
> cluster-level statistic). Note that if you want to run a two-sided test,
> you have to split the critical alpha value by setting cfg.correcttail =
> ‘alpha’; i.e. this sets cfg.alpha = 0.025, corresponding to a false
> alarm rate of 0.05 in a two-sided test. The field cfg.alpha is not
> crucial. This is because the output of ft_timelockstatistics (see
> further) contains a p-value for every cluster (calculated under the
> permutation distribution of the maximum/minimum cluster-level
> statistic). Instead of the critical values, we can also use these
> p-values to determine the significance of the clusters.”
> 
> I interpreted this to mean that I should double all the p-values I get
> in the final output, since I am running two-tailed tests. E.g., if I
> specify that I want a two-tailed test in cfg.tail and if I then get an
> output saying:
> 
> stat.posclusters
> ans =
> struct with fields:
> prob: 0.0188
> clusterstat: 160.9688
> stddev: 0.0014
> cirange: 0.0027
> 
> Then I interpret it to mean that the actual two-tailed p-value is
> 0.0376, not 0.0188. However, I’m having second thoughts about this, and
> wondering if I have this right.
> 
> I’m afraid this is kind of urgent – I’m supposed to submit slides
> tomorrow for a talk I’m giving where we analyze data using this
> function, so if you have a chance to confirm whether I am interpreting
> this correctly or not, that would be super-appreciated! Thanks so much,
> 
> Patrick
> 
>  
> 
> Patrick Dwyer
> 
> Ph.D. Student, Developmental Psychology
> 
> Neurocognitive Development Lab <http://riveralab.ucdavis.edu/>
> 
> Center for Mind and Brain, UC Davis
> 
>  
> 
> Personal Blog: http://www.autisticscholar.com/
> 
> Pronouns: he/him/his
> 
> 
> _______________________________________________
> fieldtrip mailing list
> https://mailman.science.ru.nl/mailman/listinfo/fieldtrip
> https://doi.org/10.1371/journal.pcbi.1002202
> 
_______________________________________________
fieldtrip mailing list
https://mailman.science.ru.nl/mailman/listinfo/fieldtrip
https://doi.org/10.1371/journal.pcbi.1002202