Beyond the obvious difficulty that you
have less information about the
second distribution, it is possible
to apply -ksmirnov- to such data.
However, I'd underline Rupert Miller's pithy critique of
Kolmogorov-Smirnov quoted within
[R] diagnostic plots. -qqplot- (also -ppplot-
from SSC) are graphical ways of comparing
such distributions.
Nick
[email protected]
Angelo Zago
> I am testing whether two samples have the same distributions
> by using the
> Kolmogorov Smirnov test.
> The fact is that one sample has a size of 530 observations,
> the other of
> only 25. Does this very different sample size create any
> problem? Is there
> any way to take it into account?
*
* 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/