[Eeglablist] ICA Sample Size

A. Debebe debebea at yahoo.com
Sat Nov 4 11:45:04 PST 2006


Dear All,

The central limit theorem mentions: when n is
sufficiently large, the smpling distribution of mean
of the distribution is well approximated by a normal
curve, even when the population distrbution is not
itself normal. The central limit theorem can safely be
applied if n exceeds 30.Refere, any elementary
statistics book. This explains the magic number 30.

Best regards,

Debebe asefa, PhD

--- arno <arno at salk.edu> wrote:

> Dear Asefa,
> 
> I do not agree with your number 30. It depends on
> the number of 
> channels. Also, I am not sure the number of sample
> has anything to do 
> with normality. See past messages on this subject.
> 
>
http://sccn.ucsd.edu/pipermail/eeglablist/2006/001566.html
>
http://sccn.ucsd.edu/pipermail/eeglablist/2006/001568.html
>
http://sccn.ucsd.edu/pipermail/eeglablist/2006/001570.html
> 
> Best regards,
> 
> Arno
> 
> A. Debebe wrote:
> > Dear All,
> >
> > I followed the ICA discussions of the sample size,
> a
> > minimum of 30 samples is required due to the
> reasons,
> > ICA uses statistical analysis and in any
> statistical
> > analysis you need large sample enough to apply the
> > central limit theorem. The magic numbber 30 is
> > selected to make the sample distribution normal
> even
> > when the population distribution itself is not
> normal.
> > If one takes a sample size less than 30 then one
> must
> > believe that the distribution of values in the
> > population is normal ( there must be prior
> knowledge
> > of the normal distribution).
> >
> > Regards,
> >
> > Debebe Asefa, PhD
> >
> >
> >  
> >
>
____________________________________________________________________________________
> > Low, Low, Low Rates! Check out Yahoo! Messenger's
> cheap PC-to-Phone call rates 
> > (http://voice.yahoo.com)
> >
> > _______________________________________________
> > eeglablist mailing list eeglablist at sccn.ucsd.edu
> > Eeglablist page:
> http://sccn.ucsd.edu/eeglab/eeglabmail.html
> > To unsubscribe, send an empty email to
> eeglablist-unsubscribe at sccn.ucsd.edu
> >
> >
> >   
> 
> 



 
____________________________________________________________________________________
Access over 1 million songs - Yahoo! Music Unlimited 
(http://music.yahoo.com/unlimited)




More information about the eeglablist mailing list