<?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: Cluster refining in SAS Procedures</title>
    <link>https://communities.sas.com/t5/SAS-Procedures/Cluster-refining/m-p/56610#M15811</link>
    <description>Hi.&lt;BR /&gt;
In my opinion.&lt;BR /&gt;
There is ' proc varclus' ( the name I have forgetted) which can do cluster analysis for variables which has the same principle with proc cluster but its object analysised is variables not obs.&lt;BR /&gt;
&lt;BR /&gt;
And you also can do primary component analysis for these variable to see which variables influent the whole data's variance.&lt;BR /&gt;
&lt;BR /&gt;
&lt;BR /&gt;
&lt;BR /&gt;
Ksharp</description>
    <pubDate>Fri, 31 Dec 2010 11:55:09 GMT</pubDate>
    <dc:creator>Ksharp</dc:creator>
    <dc:date>2010-12-31T11:55:09Z</dc:date>
    <item>
      <title>Cluster refining</title>
      <link>https://communities.sas.com/t5/SAS-Procedures/Cluster-refining/m-p/56606#M15807</link>
      <description>Can anyone tell me , how can I refine the already made clusters (generated by human intelligence) in SAS ? ..... that is, I already have the clusters but I need to refine those by some variables.</description>
      <pubDate>Thu, 30 Dec 2010 11:00:35 GMT</pubDate>
      <guid>https://communities.sas.com/t5/SAS-Procedures/Cluster-refining/m-p/56606#M15807</guid>
      <dc:creator>deleted_user</dc:creator>
      <dc:date>2010-12-30T11:00:35Z</dc:date>
    </item>
    <item>
      <title>Re: Cluster refining</title>
      <link>https://communities.sas.com/t5/SAS-Procedures/Cluster-refining/m-p/56607#M15808</link>
      <description>Hi&lt;BR /&gt;
&lt;BR /&gt;
This is probabely more a question to be posted to the "Statistical Procedures" forum.&lt;BR /&gt;
&lt;BR /&gt;
You normally get the best answers if you ask very specific questions, best by providing an example, describing explicitly what you have and what you need.&lt;BR /&gt;
&lt;BR /&gt;
HTH&lt;BR /&gt;
Patrick</description>
      <pubDate>Thu, 30 Dec 2010 11:09:21 GMT</pubDate>
      <guid>https://communities.sas.com/t5/SAS-Procedures/Cluster-refining/m-p/56607#M15808</guid>
      <dc:creator>Patrick</dc:creator>
      <dc:date>2010-12-30T11:09:21Z</dc:date>
    </item>
    <item>
      <title>Re: Cluster refining</title>
      <link>https://communities.sas.com/t5/SAS-Procedures/Cluster-refining/m-p/56608#M15809</link>
      <description>Hi.&lt;BR /&gt;
What proc you used?&lt;BR /&gt;
You cluster for variables or observation?&lt;BR /&gt;
And In the output there is some statistical index (such as CCC) will display the variance of this obs / variables accounts for whole data's variance.&lt;BR /&gt;
Maybe you can use primary component analysis for the multi-variables data to see which variable is the most important.&lt;BR /&gt;
&lt;BR /&gt;
BTW.Just as Patrick said why not post it in ' Statistical Procedure' forum,There is man named lvm will give you more help, He is an expert about these.&lt;BR /&gt;
&lt;BR /&gt;
&lt;BR /&gt;
Ksharp</description>
      <pubDate>Fri, 31 Dec 2010 01:02:21 GMT</pubDate>
      <guid>https://communities.sas.com/t5/SAS-Procedures/Cluster-refining/m-p/56608#M15809</guid>
      <dc:creator>Ksharp</dc:creator>
      <dc:date>2010-12-31T01:02:21Z</dc:date>
    </item>
    <item>
      <title>Re: Cluster refining</title>
      <link>https://communities.sas.com/t5/SAS-Procedures/Cluster-refining/m-p/56609#M15810</link>
      <description>Thanks to both of you.&lt;BR /&gt;
I am using PROC CLUSTER and clustering for observations. &lt;BR /&gt;
&lt;BR /&gt;
Do you wanna add something to your response after this clarification ?&lt;BR /&gt;
&lt;BR /&gt;
I have posted this to 'Statistical Procedure'  forum also.</description>
      <pubDate>Fri, 31 Dec 2010 05:48:07 GMT</pubDate>
      <guid>https://communities.sas.com/t5/SAS-Procedures/Cluster-refining/m-p/56609#M15810</guid>
      <dc:creator>deleted_user</dc:creator>
      <dc:date>2010-12-31T05:48:07Z</dc:date>
    </item>
    <item>
      <title>Re: Cluster refining</title>
      <link>https://communities.sas.com/t5/SAS-Procedures/Cluster-refining/m-p/56610#M15811</link>
      <description>Hi.&lt;BR /&gt;
In my opinion.&lt;BR /&gt;
There is ' proc varclus' ( the name I have forgetted) which can do cluster analysis for variables which has the same principle with proc cluster but its object analysised is variables not obs.&lt;BR /&gt;
&lt;BR /&gt;
And you also can do primary component analysis for these variable to see which variables influent the whole data's variance.&lt;BR /&gt;
&lt;BR /&gt;
&lt;BR /&gt;
&lt;BR /&gt;
Ksharp</description>
      <pubDate>Fri, 31 Dec 2010 11:55:09 GMT</pubDate>
      <guid>https://communities.sas.com/t5/SAS-Procedures/Cluster-refining/m-p/56610#M15811</guid>
      <dc:creator>Ksharp</dc:creator>
      <dc:date>2010-12-31T11:55:09Z</dc:date>
    </item>
  </channel>
</rss>

