<?xml version="1.0" encoding="UTF-8"?>
<rss xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:taxo="http://purl.org/rss/1.0/modules/taxonomy/" version="2.0">
  <channel>
    <title>topic Glimmix ordinal logistic regression interaction odds ratios in Statistical Procedures</title>
    <link>https://communities.sas.com/t5/Statistical-Procedures/Glimmix-ordinal-logistic-regression-interaction-odds-ratios/m-p/437985#M23095</link>
    <description>&lt;P&gt;Hi&lt;/P&gt;&lt;P&gt;I hope that this is the right forum to ask this question. I was a bit in a hurry so I couldn't make sure of it and possible previous responses.&lt;/P&gt;&lt;P&gt;When the response is binary, glimmix does a very good job giving odds ratios of about an interaction in a logistic regression model.&lt;/P&gt;&lt;P&gt;But when the response is ordinal, I get the following error&lt;/P&gt;&lt;PRE class="sasLog"&gt; ERROR: Least-squares means are not available for the multinomial distribution.&lt;/PRE&gt;&lt;P&gt;when I try a line like this&lt;/P&gt;&lt;P&gt;lsmeans treat*time / oddsratio ilink slicediff=time;&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;What can I do in such a situation to get the odds ratios in slices?&lt;/P&gt;</description>
    <pubDate>Fri, 16 Feb 2018 17:16:57 GMT</pubDate>
    <dc:creator>siyisoy</dc:creator>
    <dc:date>2018-02-16T17:16:57Z</dc:date>
    <item>
      <title>Glimmix ordinal logistic regression interaction odds ratios</title>
      <link>https://communities.sas.com/t5/Statistical-Procedures/Glimmix-ordinal-logistic-regression-interaction-odds-ratios/m-p/437985#M23095</link>
      <description>&lt;P&gt;Hi&lt;/P&gt;&lt;P&gt;I hope that this is the right forum to ask this question. I was a bit in a hurry so I couldn't make sure of it and possible previous responses.&lt;/P&gt;&lt;P&gt;When the response is binary, glimmix does a very good job giving odds ratios of about an interaction in a logistic regression model.&lt;/P&gt;&lt;P&gt;But when the response is ordinal, I get the following error&lt;/P&gt;&lt;PRE class="sasLog"&gt; ERROR: Least-squares means are not available for the multinomial distribution.&lt;/PRE&gt;&lt;P&gt;when I try a line like this&lt;/P&gt;&lt;P&gt;lsmeans treat*time / oddsratio ilink slicediff=time;&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;What can I do in such a situation to get the odds ratios in slices?&lt;/P&gt;</description>
      <pubDate>Fri, 16 Feb 2018 17:16:57 GMT</pubDate>
      <guid>https://communities.sas.com/t5/Statistical-Procedures/Glimmix-ordinal-logistic-regression-interaction-odds-ratios/m-p/437985#M23095</guid>
      <dc:creator>siyisoy</dc:creator>
      <dc:date>2018-02-16T17:16:57Z</dc:date>
    </item>
    <item>
      <title>Re: Glimmix ordinal logistic regression interaction odds ratios</title>
      <link>https://communities.sas.com/t5/Statistical-Procedures/Glimmix-ordinal-logistic-regression-interaction-odds-ratios/m-p/438047#M23103</link>
      <description>&lt;P&gt;I have seen that slice or lsmestimate statements surprisingly work for such a purpose in a plm procedure after glimmix.&lt;/P&gt;</description>
      <pubDate>Fri, 16 Feb 2018 19:11:50 GMT</pubDate>
      <guid>https://communities.sas.com/t5/Statistical-Procedures/Glimmix-ordinal-logistic-regression-interaction-odds-ratios/m-p/438047#M23103</guid>
      <dc:creator>siyisoy</dc:creator>
      <dc:date>2018-02-16T19:11:50Z</dc:date>
    </item>
  </channel>
</rss>

