Hi Jan-Mathijs,<div><br></div><div>Many thanks - I wasn't aware of there being an F test version and this has solved the problem now. Strangely, I had tried running the same dependent samples T test with only 2 conditions just to see if that would work, and for some reason, it wouldn't (I had adjusted the design matrix of course). I have now gotten it all to work though, both F test with several conditions and the T test with only 2, so I must have overlooked something previously. </div>
<div><br></div><div>Many thanks for your help!</div><div><br></div><div>Loes<br><br><div class="gmail_quote">On Wed, Mar 30, 2011 at 6:15 PM, jan-mathijs schoffelen <span dir="ltr"><<a href="mailto:jan.schoffelen@donders.ru.nl">jan.schoffelen@donders.ru.nl</a>></span> wrote:<br>
<blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex;"><div style="word-wrap:break-word">Hi Loes,<div><br></div><div>The statistical test you are trying to do, is a dependent samples T test. This can only be applied if you have a repeated measures design with 2 conditions. You have 6 conditions, and this causes the error I presume.</div>
<div>I guess what you need is probably a depsamplesF or so.</div><div><br></div><div>Best wishes,</div><div><br></div><div>Jan-Mathijs</div><div><br><div><div><div></div><div class="h5"><div>On Mar 30, 2011, at 8:21 AM, Loes Koelewijn wrote:</div>
<br></div></div><blockquote type="cite"><div><div></div><div class="h5"><span style="border-collapse:collapse;font-family:arial, sans-serif;font-size:13px"><span style="border-collapse:collapse;font-family:arial, sans-serif;font-size:13px"><div>
<span style="border-collapse:collapse;font-family:arial, sans-serif;font-size:13px"><span style="border-collapse:collapse;font-family:arial, sans-serif;font-size:13px">Hi all,</span></span></div> <div><span style="border-collapse:collapse;font-family:arial, sans-serif;font-size:13px"><span style="border-collapse:collapse;font-family:arial, sans-serif;font-size:13px"><br>
</span></span></div> I have a question about group analysis statistics of my</span><span style="border-collapse:collapse;font-family:arial, sans-serif;font-size:13px"> MEG study. I've made virtual sensors from group average images of an independent localiser run, created at several time windows, based on the group inversion. I then extracted dipole waveforms for all other conditions (6), for each subject (10), based on those virtual sensors (the study has a repeated measures design). I would now like to analyse group significance of any differences between these 6 time courses, over all time samples, corrected for multiple comparisons. I have tried to do this using FieldTrip's cluster based permutation test (Monte Carlo), independently for each virtual channel, by setting the neighbouring channels to 0. However, I get an error about the design matrix when running ft_timelockstatistics.</span></span><div>
<font face="arial, sans-serif"><span style="border-collapse:collapse"><br></span></font></div><div><font face="arial, sans-serif"><span style="border-collapse:collapse">Matlab's output is the following:</span></font></div>
<div><span style="border-collapse:collapse;font-family:arial, sans-serif"><br></span></div><div><span style="border-collapse:collapse;font-family:arial, sans-serif">selected 1 channels</span></div> <div><font face="arial, sans-serif"><span style="border-collapse:collapse"><div>
selected 251 time bins</div><div>selected 1 frequency bins</div><div>Using the gradiometer configuration from the dataset.</div> <div>there are on average 0.0 neighbours per channel</div><div>using "statistics_montecarlo" for the statistical testing</div>
<div>using "statfun_depsamplesT" for the single-sample statistics</div><div> constructing randomized design</div><div>total number of measurements = 60</div><div>total number of variables = 2</div><div>
number of independent variables = 1</div><div>number of unit variables = 1</div> <div>number of within-cell variables = 0</div><div>number of control variables = 0</div><div>using a permutation resampling approach</div>
<div>repeated measurement in variable 2 over 6 levels</div><div>number of repeated measurements in each level is 10 10 10 10 10 10 </div> <div>computing a parmetric threshold for clustering</div><div>Error using ==> statfun_depsamplesT at 78</div>
<div>Invalid specification of the design array.</div><div>??? Error using ==> statistics_montecarlo at 217</div> <div>could not determine the parametric critical value for clustering</div><div><br></div><div>Error in ==> statistics_wrapper at 285</div>
<div> [stat, cfg] = statmethod(cfg, dat, cfg.design, 'issource',issource);</div> <div><br></div><div>Error in ==> ft_timelockstatistics at 117</div><div>[stat, cfg] = statistics_wrapper(cfg, varargin{:});</div>
</span></font></div><div><font face="arial, sans-serif"><span style="border-collapse:collapse"><br> </span></font></div><div><font face="arial, sans-serif"><span style="border-collapse:collapse">Could anybody help me in the direction of what is going wrong here? I wondered earlier if my data structures were incorrect, but these were created with ft_timelockgrandaverage, keeping the individual data. This is what I ran:</span></font></div>
<div><font face="arial, sans-serif"><span style="border-collapse:collapse"><br></span></font></div><div><font face="arial, sans-serif"><span style="border-collapse:collapse">[stat]=ft_timelockstatistics(cfg,cond1,cond2,cond3,cond4,cond5,cond6);</span></font></div>
<div><font face="arial, sans-serif"><span style="border-collapse:collapse"><br></span></font></div><div><font face="arial, sans-serif"><div><span style="border-collapse:collapse">cfg = </span></div> <div><span style="border-collapse:collapse"><br>
</span></div><div><span style="border-collapse:collapse"> channel: 'Occipital_Inf_RR_X'</span></div> <div><span style="border-collapse:collapse"> latency: [-0.2000 0.8000]</span></div><div>
<span style="border-collapse:collapse"> method: 'montecarlo'</span></div> <div><span style="border-collapse:collapse"> statistic: 'depsamplesT'</span></div><div><span style="border-collapse:collapse"> correctm: 'cluster'</span></div>
<div><span style="border-collapse:collapse"> clusteralpha: 0.0500</span></div><div><span style="border-collapse:collapse"> clusterstatistic: 'maxsum'</span></div> <div><span style="border-collapse:collapse"> tail: 0</span></div>
<div><span style="border-collapse:collapse"> clustertail: 0</span></div><div><span style="border-collapse:collapse"> alpha: 0.0250</span></div> <div><span style="border-collapse:collapse"> numrandomization: 500</span></div>
<div><span style="border-collapse:collapse"> design: [2x60 double]</span></div> <div><span style="border-collapse:collapse"> uvar: 2</span></div><div><span style="border-collapse:collapse"> ivar: 1</span></div>
<div><span style="border-collapse:collapse"><br> </span></div><div><span style="border-collapse:collapse">cfg.design is 2*60, with the first row (ivar) [1:10,1:10,1:10 etc], </span><span style="border-collapse:collapse">second row (uvar) [ones(1,10),ones(1,10)*2, etc].</span></div>
<div><span style="border-collapse:collapse">I initially had ivar and uvar reversed, but I got the same error.</span></div></font><div><span style="border-collapse:collapse;font-family:arial, sans-serif;font-size:13px"><span style="border-collapse:collapse;font-family:arial, sans-serif;font-size:13px"><br>
</span></span></div><div><span style="border-collapse:collapse;font-family:arial, sans-serif;font-size:13px"><span style="border-collapse:collapse;font-family:arial, sans-serif;font-size:13px">And this is the format of each data structure:</span></span></div>
<div><span style="border-collapse:collapse;font-family:arial, sans-serif;font-size:13px"><span style="border-collapse:collapse;font-family:arial, sans-serif;font-size:13px"><br></span></span></div> <div><span style="border-collapse:collapse;font-family:arial, sans-serif;font-size:13px"><span style="border-collapse:collapse;font-family:arial, sans-serif;font-size:13px"><div>
label: {'Occipital_Inf_RR_X'}</div> <div> fsample: 250</div><div> avg: [1x826 double]</div><div> var: [1x826 double]</div><div> time: [1x826 double]</div><div> individual: [10x1x826 double]</div>
<div> dimord: 'subj_chan_time'</div> <div> cfg: [1x1 struct]</div><div> grad: [1x1 struct]</div></span></span></div><div><span style="border-collapse:collapse;font-family:arial, sans-serif;font-size:13px"><span style="border-collapse:collapse;font-family:arial, sans-serif;font-size:13px"><br>
</span></span></div><div><span style="border-collapse:collapse;font-family:arial, sans-serif;font-size:13px"><span style="border-collapse:collapse;font-family:arial, sans-serif;font-size:13px">Apologies for the massive email, but I was hoping this is enough info for someone to have more of a clue than I do?</span></span></div>
<div><span style="border-collapse:collapse;font-family:arial, sans-serif;font-size:13px"><span style="border-collapse:collapse;font-family:arial, sans-serif;font-size:13px"><br></span></span></div> <div><font face="arial, sans-serif"><span style="border-collapse:collapse">Kind regards,</span></font></div>
<div><font face="arial, sans-serif"><span style="border-collapse:collapse"><br> </span></font></div><div><font face="arial, sans-serif"><span style="border-collapse:collapse">Loes</span></font></div><div><span style="border-collapse:collapse;font-family:arial, sans-serif;font-size:13px"><span style="border-collapse:collapse;font-family:arial, sans-serif;font-size:13px"><br>
</span></span></div><div><font face="arial, sans-serif"><span style="border-collapse:collapse">PS <span style="font-family:arial;border-collapse:separate"><span style="border-collapse:collapse;font-family:arial, sans-serif;font-size:13px"><span style="border-collapse:collapse;font-family:arial, sans-serif;font-size:13px">Do let me know if you think this approach is wrong in the first place. I was trying to avoid pre-setting time windows for image-based statistics, as we do not really have strong a priori expectations for times.</span></span></span></span></font></div>
<div><font face="arial, sans-serif"><span style="border-collapse:collapse"><br clear="all"></span></font>-- <br><span style="font-family:arial, sans-serif;font-size:13px;border-collapse:collapse">Loes Koelewijn<br> PhD Candidate<br>
Macquarie Centre for Cognitive Science (MACCS)<br>Macquarie University<br>Sydney NSW 2109<br>Australia<br><br>Ph: +61 2 9850 4135<br>Fax: +61 2 9850 6059<br>email: <a href="mailto:loes.koelewijn@mq.edu.au" style="color:rgb(148, 46, 6)" target="_blank">loes.koelewijn@mq.edu.au</a></span><br>
</div></div></div></div> _______________________________________________<br>fieldtrip mailing list<br><a href="mailto:fieldtrip@donders.ru.nl" target="_blank">fieldtrip@donders.ru.nl</a><br><a href="http://mailman.science.ru.nl/mailman/listinfo/fieldtrip" target="_blank">http://mailman.science.ru.nl/mailman/listinfo/fieldtrip</a></blockquote>
</div><br><div> <span style="border-collapse:separate;color:rgb(0, 0, 0);font-family:Helvetica;font-style:normal;font-variant:normal;font-weight:normal;letter-spacing:normal;line-height:normal;text-align:auto;text-indent:0px;text-transform:none;white-space:normal;word-spacing:0px;font-size:medium"><div style="word-wrap:break-word">
<span style="border-collapse:separate;color:rgb(0, 0, 0);font-family:Helvetica;font-size:medium;font-style:normal;font-variant:normal;font-weight:normal;letter-spacing:normal;line-height:normal;text-indent:0px;text-transform:none;white-space:normal;word-spacing:0px"><div style="word-wrap:break-word">
<div>Dr. J.M. (Jan-Mathijs) Schoffelen </div><div>Donders Institute for Brain, Cognition and Behaviour, <br>Centre for Cognitive Neuroimaging,<br>Radboud University Nijmegen, The Netherlands</div><div><a href="mailto:J.Schoffelen@donders.ru.nl" target="_blank">J.Schoffelen@donders.ru.nl</a></div>
<div>Telephone: 0031-24-3614793</div></div></span></div></span> </div><br></div></div><br>_______________________________________________<br>
fieldtrip mailing list<br>
<a href="mailto:fieldtrip@donders.ru.nl">fieldtrip@donders.ru.nl</a><br>
<a href="http://mailman.science.ru.nl/mailman/listinfo/fieldtrip" target="_blank">http://mailman.science.ru.nl/mailman/listinfo/fieldtrip</a><br></blockquote></div><br><br clear="all"><br>-- <br><span style="font-family:arial, sans-serif;font-size:13px;border-collapse:collapse">Loes Koelewijn<br>
PhD Candidate<br>Macquarie Centre for Cognitive Science (MACCS)<br>Macquarie University<br>Sydney NSW 2109<br>Australia<br><br>Ph: +61 2 9850 4135<br>Fax: +61 2 9850 6059<br>email: <a href="mailto:loes.koelewijn@mq.edu.au" style="color:rgb(148, 46, 6)" target="_blank">loes.koelewijn@mq.edu.au</a></span><br>
</div>