Not the answer you seek, but also check out [R] diagplots
and particularly -qnorm-. The manual entry carries
a splendid quotation from Rupert Miller on why such
a plot is typically much more valuable than K-S
or chi-square for the underlying problem.
Nick
[email protected]
Michael Blasnik
> Is var1 already standardized? If not, I suggest you look
> at the help file
> and follow the example there, where the variable is first
> summarized and
> then compared to standardized values. You may also want to
> follow the help
> file's advice about sktest and swilk.
Michael Carney
> > >I am trying to conduct a Kolmogorov-Smirnov test to
> determine if a set of
> > >data is distributed normally. I am using the command
> >
> > > ksmirnov var1 = normprob(var1)
> >
> > But using this command, I am getting obviously incorrect
> D statistics. (I
> > have tried the same command with a small data set to
> which I have computed
> > the correct answer by hand, and stata gives incorrect D
> values for that
> > small data set as well.) Am I missing something in the
> command line?
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
