[Homer-users] Statistical Data for Averages in Homer

[thuppert]

The variance (in the case of Averaged but NOT deconvolved) should be
calculated when you hit <Average or <Average All>.  At that point you should
be able to view the std-dev or std-err on the plot window.  If you
deconvolved, then these fields won't exist  (they have different meanings in
linear regression).

The statistics options were things that I had been putting into HomER.  They
are barely there in the current version, but more fully explored in the next
release (give me anouther month or so of FULL debugging).  If you want to
get at the variance, you can save the data.  Re-open it in matlab and the
average/var for the HRF are stored in:

DOT.data(file).Avg -- for dOD
DOT.data(file).AvgC -- for dConc

DOT.data(file).AvgStd -- for Std-Dev dOD
DOT.data(file).AvgCStd -- for dConc

DOT.data(file).AvgStdErr -- for Std-Error dOD
DOT.data(file).AvgCStdErr -- for dConc


...and

DOT.dataAvg.Avg -- for dOD
DOT.dataAvg.AvgC -- for dConc

DOT.dataAvg.AvgStd -- for Std-Dev dOD
DOT.dataAvg.AvgCStd -- for dConc

DOT.dataAvg.AvgStdErr -- for Std-Error dOD
DOT.dataAvg.AvgCStdErr -- for dConc


...
I guess you could calculate t-statistics as t_stats =
DOT.dataAvg.Avg./DOT.dataAvg.AvgStd;

As far as residuals, F-stats, effects stats, etc... its all in the next
release version.  But I didn't have it ready in the last release.  These
stats require the Matlab Stats toolbox and soem of this is done for the
deconvolution in the current version... but not averaging.  In the next
version, its done for all analysis and the stats toolbox is NOT required (so
don't go out and spend the hundred $$ to purchase it just yet).

-Ted




-----Original Message-----
From: homer-users-bounces at nmr.mgh.harvard.edu
[mailto:homer-users-bounces at nmr.mgh.harvard.edu]On Behalf Of Margaret
Duff
Sent: Thursday, February 17, 2005 12:01 PM
To: homer-users at nmr.mgh.harvard.edu
Subject: [Homer-users] Statistical Data for Averages in Homer


Hi,  I wanted to perform some statistical analysis on my averaged delta
optical density waveforms, but there appears to be no way to get the
variance data that would be associated with these averages.  There is an
option to show statistical data, but when I select that it tells me none
has been created.  Does anyone know how to calculate the statistics or
where this information may be found?  Thanks, Margaret

_______________________________________________
Homer-users mailing list
Homer-users at nmr.mgh.harvard.edu
https://mail.nmr.mgh.harvard.edu/mailman/listinfo/homer-users