<?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 Re: Seeing the mean/% of a variable held out of cluster analysis in SAS Data Science</title>
    <link>https://communities.sas.com/t5/SAS-Data-Science/Seeing-the-mean-of-a-variable-held-out-of-cluster-analysis/m-p/286238#M4250</link>
    <description>Thanks. But I was hoping that there would be something within the cluster or SOM nodes that would display stats on variables not im the actual analysis.</description>
    <pubDate>Thu, 21 Jul 2016 19:48:22 GMT</pubDate>
    <dc:creator>DocMartin</dc:creator>
    <dc:date>2016-07-21T19:48:22Z</dc:date>
    <item>
      <title>Seeing the mean/% of a variable held out of cluster analysis</title>
      <link>https://communities.sas.com/t5/SAS-Data-Science/Seeing-the-mean-of-a-variable-held-out-of-cluster-analysis/m-p/285599#M4227</link>
      <description>I've been using EM to do cluster analysis and SOM. The graphic in the Results is partially helpful. What I'd like to do is to color each cluster by the mean (interval variable) or % (binary variable) not used in the clustering. Does anyone have any ideas? Thanks! Andrew</description>
      <pubDate>Tue, 19 Jul 2016 18:13:38 GMT</pubDate>
      <guid>https://communities.sas.com/t5/SAS-Data-Science/Seeing-the-mean-of-a-variable-held-out-of-cluster-analysis/m-p/285599#M4227</guid>
      <dc:creator>DocMartin</dc:creator>
      <dc:date>2016-07-19T18:13:38Z</dc:date>
    </item>
    <item>
      <title>Re: Seeing the mean/% of a variable held out of cluster analysis</title>
      <link>https://communities.sas.com/t5/SAS-Data-Science/Seeing-the-mean-of-a-variable-held-out-of-cluster-analysis/m-p/285614#M4232</link>
      <description>&lt;P&gt;Hi.&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;P&gt;The Segment Profile node gives the option to include Report variables (including the target variable) in the segment profile. Depending on the report variable's measurement level, this will produce either a donut plot (nominal) or histogram (interval) for each report variable for each segment.&amp;nbsp;&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;P&gt;Hope that helps.&amp;nbsp;&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;P&gt;Ray&lt;/P&gt;</description>
      <pubDate>Tue, 19 Jul 2016 19:17:47 GMT</pubDate>
      <guid>https://communities.sas.com/t5/SAS-Data-Science/Seeing-the-mean-of-a-variable-held-out-of-cluster-analysis/m-p/285614#M4232</guid>
      <dc:creator>rayIII</dc:creator>
      <dc:date>2016-07-19T19:17:47Z</dc:date>
    </item>
    <item>
      <title>Re: Seeing the mean/% of a variable held out of cluster analysis</title>
      <link>https://communities.sas.com/t5/SAS-Data-Science/Seeing-the-mean-of-a-variable-held-out-of-cluster-analysis/m-p/286238#M4250</link>
      <description>Thanks. But I was hoping that there would be something within the cluster or SOM nodes that would display stats on variables not im the actual analysis.</description>
      <pubDate>Thu, 21 Jul 2016 19:48:22 GMT</pubDate>
      <guid>https://communities.sas.com/t5/SAS-Data-Science/Seeing-the-mean-of-a-variable-held-out-of-cluster-analysis/m-p/286238#M4250</guid>
      <dc:creator>DocMartin</dc:creator>
      <dc:date>2016-07-21T19:48:22Z</dc:date>
    </item>
  </channel>
</rss>

