<?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: Proc adaptivereg:  fixing a knot value in Statistical Procedures</title>
    <link>https://communities.sas.com/t5/Statistical-Procedures/Proc-adaptivereg-fixing-a-knot-value/m-p/401319#M20925</link>
    <description>&lt;P&gt;Hi Warren,&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;Thanks a lot for your reply.&amp;nbsp; I did try that (in addition to the original variables), and the model ended up selecting one of the two manually created basis.&amp;nbsp; So I finally ended up creating an indicator variable instead with a value of 1 after the knot and a value of 0 before the knot, and using this indicator as a class variable.&amp;nbsp; It isn't quite what I was looking for, but it&amp;nbsp;is better than not having this knot in.&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;Thanks&amp;nbsp;again,&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;Yves 2017&lt;/P&gt;</description>
    <pubDate>Thu, 05 Oct 2017 13:08:36 GMT</pubDate>
    <dc:creator>Yves2017</dc:creator>
    <dc:date>2017-10-05T13:08:36Z</dc:date>
    <item>
      <title>Proc adaptivereg:  fixing a knot value</title>
      <link>https://communities.sas.com/t5/Statistical-Procedures/Proc-adaptivereg-fixing-a-knot-value/m-p/400356#M20870</link>
      <description>&lt;P&gt;I would like to know if within SAS 9.4 Proc Adaptivereg there is a way to fix the value of&amp;nbsp;one knot.&amp;nbsp; I understand that the strength of the procedure is to identify the knots by itself, but I was wondering if it was possible to let it identify the other knots, but to stipulate the value of one knot.&amp;nbsp; I know that maxbasis helps in fixing the total number of knots in the final model, but I can't find a way to do what I would like it to do.&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;Thanks,&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;Yves2017&amp;nbsp;&lt;/P&gt;</description>
      <pubDate>Mon, 02 Oct 2017 17:40:54 GMT</pubDate>
      <guid>https://communities.sas.com/t5/Statistical-Procedures/Proc-adaptivereg-fixing-a-knot-value/m-p/400356#M20870</guid>
      <dc:creator>Yves2017</dc:creator>
      <dc:date>2017-10-02T17:40:54Z</dc:date>
    </item>
    <item>
      <title>Re: Proc adaptivereg:  fixing a knot value</title>
      <link>https://communities.sas.com/t5/Statistical-Procedures/Proc-adaptivereg-fixing-a-knot-value/m-p/400362#M20871</link>
      <description>&lt;P&gt;I suppose you could manually create a two-column piece-wise linear basis at a prespecified knot and use that as input instead of (or perhaps in addition to) the original variable.&amp;nbsp; I have never tried anything like that. There is no guarantee that adaptive reg will use the effects that you put in. Please let me know if that works.&lt;/P&gt;</description>
      <pubDate>Mon, 02 Oct 2017 17:48:45 GMT</pubDate>
      <guid>https://communities.sas.com/t5/Statistical-Procedures/Proc-adaptivereg-fixing-a-knot-value/m-p/400362#M20871</guid>
      <dc:creator>WarrenKuhfeld</dc:creator>
      <dc:date>2017-10-02T17:48:45Z</dc:date>
    </item>
    <item>
      <title>Re: Proc adaptivereg:  fixing a knot value</title>
      <link>https://communities.sas.com/t5/Statistical-Procedures/Proc-adaptivereg-fixing-a-knot-value/m-p/401319#M20925</link>
      <description>&lt;P&gt;Hi Warren,&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;Thanks a lot for your reply.&amp;nbsp; I did try that (in addition to the original variables), and the model ended up selecting one of the two manually created basis.&amp;nbsp; So I finally ended up creating an indicator variable instead with a value of 1 after the knot and a value of 0 before the knot, and using this indicator as a class variable.&amp;nbsp; It isn't quite what I was looking for, but it&amp;nbsp;is better than not having this knot in.&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;Thanks&amp;nbsp;again,&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;Yves 2017&lt;/P&gt;</description>
      <pubDate>Thu, 05 Oct 2017 13:08:36 GMT</pubDate>
      <guid>https://communities.sas.com/t5/Statistical-Procedures/Proc-adaptivereg-fixing-a-knot-value/m-p/401319#M20925</guid>
      <dc:creator>Yves2017</dc:creator>
      <dc:date>2017-10-05T13:08:36Z</dc:date>
    </item>
  </channel>
</rss>

