topic Npar1way exact Median Test in Statistical Procedures https://communities.sas.com/t5/Statistical-Procedures/Npar1way-exact-Median-Test/m-p/48777#M2173 <HTML><HEAD></HEAD><BODY><P>Emily,</P><P></P><P>I don't understand your question.&nbsp; It is not unusual for the group median to equal a value in the data.&nbsp; Where it gets somewhat messier is in that the definition of "median" can vary and that can impact the estimations.&nbsp; Note that even though these p-values are called "exact" they are not the brute-force computations that we learned in graduate school (those approaches rapidly become prohibitive when the sample size exceeds 10).</P><P></P><P>Perhaps you could read the documentation referenced in </P><P><A class="jive-link-external-small" href="http://support.sas.com/documentation/cdl/en/statug/63962/HTML/default/viewer.htm#statug_npar1way_a0000000203.htm">http://support.sas.com/documentation/cdl/en/statug/63962/HTML/default/viewer.htm#statug_npar1way_a0000000203.htm</A></P><P>and reframe it.</P><P></P><P>Doc Muhlbaier</P><P>Duke</P></BODY></HTML> Wed, 16 Nov 2011 18:56:28 GMT Doc_Duke 2011-11-16T18:56:28Z Npar1way exact Median Test https://communities.sas.com/t5/Statistical-Procedures/Npar1way-exact-Median-Test/m-p/48776#M2172 <HTML><HEAD></HEAD><BODY><P>Can anyone eplain where the p-values come from if the median is equal to 1 or more of the data values in each group?</P><P></P><P>Thanks alot</P></BODY></HTML> Wed, 16 Nov 2011 16:57:10 GMT https://communities.sas.com/t5/Statistical-Procedures/Npar1way-exact-Median-Test/m-p/48776#M2172 Emily 2011-11-16T16:57:10Z Npar1way exact Median Test https://communities.sas.com/t5/Statistical-Procedures/Npar1way-exact-Median-Test/m-p/48777#M2173 <HTML><HEAD></HEAD><BODY><P>Emily,</P><P></P><P>I don't understand your question.&nbsp; It is not unusual for the group median to equal a value in the data.&nbsp; Where it gets somewhat messier is in that the definition of "median" can vary and that can impact the estimations.&nbsp; Note that even though these p-values are called "exact" they are not the brute-force computations that we learned in graduate school (those approaches rapidly become prohibitive when the sample size exceeds 10).</P><P></P><P>Perhaps you could read the documentation referenced in </P><P><A class="jive-link-external-small" href="http://support.sas.com/documentation/cdl/en/statug/63962/HTML/default/viewer.htm#statug_npar1way_a0000000203.htm">http://support.sas.com/documentation/cdl/en/statug/63962/HTML/default/viewer.htm#statug_npar1way_a0000000203.htm</A></P><P>and reframe it.</P><P></P><P>Doc Muhlbaier</P><P>Duke</P></BODY></HTML> Wed, 16 Nov 2011 18:56:28 GMT https://communities.sas.com/t5/Statistical-Procedures/Npar1way-exact-Median-Test/m-p/48777#M2173 Doc_Duke 2011-11-16T18:56:28Z