topic Mann-Whitney Rank Sum test in Statistical Procedures https://communities.sas.com/t5/Statistical-Procedures/Mann-Whitney-Rank-Sum-test/m-p/25377#M898 <HTML><HEAD></HEAD><BODY><P>I am wondering what procedure in SAS will provide Mann-Whitney Rank Sum test for two sample test.</P><P>Thanks,</P></BODY></HTML> Thu, 08 Mar 2012 15:48:05 GMT O6688 2012-03-08T15:48:05Z Mann-Whitney Rank Sum test https://communities.sas.com/t5/Statistical-Procedures/Mann-Whitney-Rank-Sum-test/m-p/25377#M898 <HTML><HEAD></HEAD><BODY><P>I am wondering what procedure in SAS will provide Mann-Whitney Rank Sum test for two sample test.</P><P>Thanks,</P></BODY></HTML> Thu, 08 Mar 2012 15:48:05 GMT https://communities.sas.com/t5/Statistical-Procedures/Mann-Whitney-Rank-Sum-test/m-p/25377#M898 O6688 2012-03-08T15:48:05Z Mann-Whitney Rank Sum test https://communities.sas.com/t5/Statistical-Procedures/Mann-Whitney-Rank-Sum-test/m-p/25378#M899 <HTML><HEAD></HEAD><BODY><P>Proc Npar1way with the Wilcoxon option will do this for you.</P><P><BR />Regards,</P><P></P><P>Keith</P></BODY></HTML> Thu, 08 Mar 2012 15:59:07 GMT https://communities.sas.com/t5/Statistical-Procedures/Mann-Whitney-Rank-Sum-test/m-p/25378#M899 Keith 2012-03-08T15:59:07Z Mann-Whitney Rank Sum test https://communities.sas.com/t5/Statistical-Procedures/Mann-Whitney-Rank-Sum-test/m-p/25379#M900 <HTML><HEAD></HEAD><BODY><P>Thank you very much.</P><P></P><P>I did so, but the results are different from the SPSS results, which reported by Mann-Whitney Rank Sum test.</P><P>What is different between 'Normal Approximation' and ' t Approximation' for the Statistic?</P><P></P><P>If I have a small sample size (&lt;10), should I use EXACT test?</P><P></P><P>Thank you again in advance.</P><P>A</P></BODY></HTML> Thu, 08 Mar 2012 16:37:23 GMT https://communities.sas.com/t5/Statistical-Procedures/Mann-Whitney-Rank-Sum-test/m-p/25379#M900 O6688 2012-03-08T16:37:23Z Mann-Whitney Rank Sum test https://communities.sas.com/t5/Statistical-Procedures/Mann-Whitney-Rank-Sum-test/m-p/25380#M901 <HTML><HEAD></HEAD><BODY><P>The differences in approximations are in the documentation.&nbsp; The approximations are for larger samples.</P><P></P><P>With a small sample the exact test is better.</P><P></P><P>Lastly, the differences with SPSS may have to do with the use of a continuity correction in the approximations.&nbsp; Again, see the documentation.</P><P></P><P>Doc Muhlbaier</P><P>Duke</P></BODY></HTML> Thu, 08 Mar 2012 19:53:38 GMT https://communities.sas.com/t5/Statistical-Procedures/Mann-Whitney-Rank-Sum-test/m-p/25380#M901 Doc_Duke 2012-03-08T19:53:38Z Mann-Whitney Rank Sum test https://communities.sas.com/t5/Statistical-Procedures/Mann-Whitney-Rank-Sum-test/m-p/25381#M902 <HTML><HEAD></HEAD><BODY><P>Thank you very much.</P><P>It is helpful.</P><P>A</P></BODY></HTML> Fri, 09 Mar 2012 14:37:58 GMT https://communities.sas.com/t5/Statistical-Procedures/Mann-Whitney-Rank-Sum-test/m-p/25381#M902 O6688 2012-03-09T14:37:58Z