permutation test for more than 2 conditions

[Andrew Smart]

Hi,
I found finv.m in the statistics toolbox and the test seems to work, but any
advice is greatly appreciated!

thanks
andy

----- Original Message -----
From: Andrew Smart <andrew.smart at nyu.edu>
Date: Monday, September 24, 2007 5:45 pm
Subject: [FIELDTRIP] permutation test for more than 2 conditions
To: FIELDTRIP at NIC.SURFNET.NL

> Hi,
> I would like to test for a main effect using the cluster-based
> permutation test (a one-way ANOVA?)
>
> I have set up the design matrix as follows:
>
> subj=16;
> design=zeros(2,3*subj);
> for i=1:subj
>     design(1,i)=i;
> end
> for i=1:subj
>     design(1,subj+i)=i;
> end
> for i=1:subj
>     design(1,subj*2+i)=i;
> end
> design(2,1:subj)=1;
> design(2,subj+1:2*subj)=2;
> design(2,subj*2+1:3*subj)=3;
>
> cfg.design = design;
> cfg.uvar=1;
> cfg.ivar=2;
>
>
> and the cfg has
>
> cfg.statistic = 'depsamplesF';
> cfg.tail=1;
> cfg.alpha = 0.05;
> cfg.numrandomization = 500;
>
> The following error comes up in statfun_depsamplesF:
> Undefined function or method 'finv' for input arguments of type 'double'.
> from these lines:
> if cfg.tail==1
>     s.critval = ((nunits-1).*ncontrasts./(nunits-ncontrasts)).*finv(1-
cfg.alpha,s.dfnum,s.dfdenom);
>   end;
>
> And then it crashes because it cannot determine the parametric
> critical value for clustering. What
> is "finv"?
>
> Thank you for any help,
> andy
>
> ----------------------------------
> The aim of this list is to facilitate the discussion between users of
> the FieldTrip  toolbox, to share experiences and to discuss new ideas
> for MEG and EEG analysis. See also

----------------------------------
The aim of this list is to facilitate the discussion between users of the FieldTrip  toolbox, to share experiences and to discuss new ideas for MEG and EEG analysis. See also http://listserv.surfnet.nl/archives/fieldtrip.html and http://www.ru.nl/fcdonders/fieldtrip.