Re: Mann-Whitney

[John Darrington]

On Tue, Jan 01, 2013 at 09:27:22AM +0000, JuleinMalang wrote:
     Hello! My question is rather into Interpretation of Mann-Whitney in PSPP, 
maybe
     somebody can help. Would be great! (:
     
     I performed u-test.
     My Syntax:
     
     NPAR TESTS
     /MANN-WHITNEY = age BY sex (1, 2)
     
     As a result it showed "Asymp. Sig. (2-tailed)" = 0,00 , z was infinite.
     
     To me that means, that the groups are significantly different. Which was
     confusing me, as they are almost the same. So I calculated again in two
     different Browser-Programs. Both showed p(2-tailed) = 0,91 and z = 0,11 
Which is
     much more probable for that data.
     Does anybody have an idea what I could have done wrong?
     

This would suggest that one of the groups has no members.  Are you sure that 1 
and 2
are the correct categorical values?  Perhaps it should be 0 and 1 ?

What do you see in the "Ranks" box that the command produces?

J'



-- 
PGP Public key ID: 1024D/2DE827B3 
fingerprint = 8797 A26D 0854 2EAB 0285  A290 8A67 719C 2DE8 27B3
See http://keys.gnupg.net or any PGP keyserver for public key.

signature.asc
Description: Digital signature