Date:         Fri, 14 Oct 2005 15:14:54 -0500
Reply-To:     "Swank, Paul R" <Paul.R.Swank@UTH.TMC.EDU>
Sender:       "SAS(r) Discussion" <SAS-L@LISTSERV.UGA.EDU>
From:         "Swank, Paul R" <Paul.R.Swank@UTH.TMC.EDU>
Subject:      Re: Kolmogorov-Smirnov Statistic--What is it?
Comments: To: "Nick ." <ni14@MAIL.COM>
Content-Type: text/plain; charset="us-ascii"

That it is unlikely the two population distributions are the same
because if they were the same there is an extremely small chance that
you sample data would give you a KS statistic that large.. Whether that
is a good thing or a bad thing depends on what your hypothesis was. It
also does not tell you how the distributions differ, but only that we
would expect them to differ.


Paul R. Swank, Ph.D.
Professor, Developmental Pediatrics
Director of Research, Center for Improving the Readiness of Children for
Learning and Education (C.I.R.C.L.E.)
Medical School
UT Health Science Center at Houston

-----Original Message-----
From: SAS(r) Discussion [mailto:SAS-L@LISTSERV.UGA.EDU] On Behalf Of
Nick .
Sent: Friday, October 14, 2005 1:52 PM
To: SAS-L@LISTSERV.UGA.EDU
Subject: Kolmogorov-Smirnov Statistic--What is it?

Thanks Paul. Paul replied


>>I'm sorry but "if the KS statistic exceeds 1.63 there is only a 1%
>>chance that the distributions are really the same" is not accurate. If

>>there were no differences in the distributions then we would expect a
KS statistic of 1.63 or greater only 1% of the time.

I just asked Talbot to explain why do I care about the distributions
being the same or being different using the KS statistic. Is it good for
the model, then, for KS to be > 1.63 or < 1.63? WHY????

In my example I posted earlier, my KS was about 7 or 8 which is much
greater than 1.63. What does that tell me?

Thanks.

NICK




--
___________________________________________________
Play 100s of games for FREE! http://games.mail.com/