Date:         Tue, 6 Sep 2005 16:05:33 +0200
Reply-To:     Marta García-Granero
              <biostatistics@terra.es>
Sender:       "SPSSX(r) Discussion" <SPSSX-L@LISTSERV.UGA.EDU>
From:         Marta García-Granero
              <biostatistics@terra.es>
Organization: Asesoría Bioestadística
Subject:      Re: Post-hoc Test for Kruskal-Wallis
In-Reply-To:  <0IME00JE3DR0V9X2@vms048.mailsrvcs.net>
Content-Type: text/plain; charset=ISO-8859-15

Hi Frank,

To simplify the task of running pairwise Mann-Whitney's U tests, you
can use the following macro:

http://www.spsstools.net/Syntax/T-Test/MultipleMann-WhitneyTests.txt

Also, instead of Bonferroni (too conservative), you can select other
methods of adjusting the p-values (more sensitive), while controlling
the experimentwise alpha level:

http://www.spsstools.net/Syntax/Unclassified/AdjustedP-ValuesAlgorithms.txt

As a matter of fact, if you had SPSS 12 (or newer), you could use OMS
to extract the p-values and combine both macros into one. But you tell
you have SPSS 10.1.

HTH

Marta

FJG> Can anyone suggest a post-hoc comparison test, using SPSS, as a follow-up to
FJG> the Kruskall-Wallis Test? I am looking for a pairwise ranking post-hoc test
FJG> that controls the significance level for the entire family of comparisons.
FJG> Does SPSS offer this feature? I am using version 10.1.