Chuck Cleland wrote:
> Johannes Hartig wrote:
> > (1) Where does the standard error I get from SPSS come
> > from? I think it should be a simple formula, but I don't find
> > it...
>
> An approximation is sqrt(6/n)
>
> From SPSS algorithms, SE of Skewness is
>
> sqrt( (6 * n * (n - 1)) / ( (n - 2) * (n + 1) * (n + 3) )
>
> where n is the sample size.
>
> > (3) SPSS online help says "A skewness value greater than 1 generally
> > indicates a distribution that differs significantly from a normal
> > distribution.". Why this?
>
> My guess is that it is because for any sample size greater than about
> 20, Skew >=1 / SE of Skew is going to lead to z values greater than
> 1.96.
>
> HTH,
> Chuck
>
Yes, this helps :-)
Thanks,
Johannes
=================================================================
Instructions for joining and leaving this list and remarks about
the problem of INAPPROPRIATE MESSAGES are available at
http://jse.stat.ncsu.edu/
=================================================================
