<?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: piecewise regression in SAS Procedures</title>
    <link>https://communities.sas.com/t5/SAS-Procedures/piecewise-regression/m-p/236049#M55191</link>
    <description>&lt;P&gt;There have been several papers written on this topic.&amp;nbsp; You will need one parameter for each location where you think the derivative is discontinuous. One easy-to-read paper is by &lt;A href="http://people.stat.sfu.ca/~cschwarz/Stat-650/Notes/PDFbigbook-SAS/SAS-part018.pdf" target="_self"&gt;Schwarz (2015)&lt;/A&gt;.&amp;nbsp; It is the similar to &lt;A href="http://www.ats.ucla.edu/stat/sas/faq/nlin_optimal_knots.htm" target="_self"&gt;an example from the UCLA web site&lt;/A&gt;. They both include code for PROC NLIN, although the example only has a single "elbow" point where the PL curve changes slope.&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;</description>
    <pubDate>Mon, 23 Nov 2015 18:27:34 GMT</pubDate>
    <dc:creator>Rick_SAS</dc:creator>
    <dc:date>2015-11-23T18:27:34Z</dc:date>
    <item>
      <title>piecewise regression</title>
      <link>https://communities.sas.com/t5/SAS-Procedures/piecewise-regression/m-p/235996#M55186</link>
      <description>&lt;P&gt;Hello everyone,&lt;/P&gt;&lt;P&gt;I am new to SAS, although I have used Program R a little in the past. &amp;nbsp;I need to run a piecewise regression/multi-phase regression for a data set that will have either two or three linear segments, and is continuous. &amp;nbsp;I don't know which, but it will be one of the two. &amp;nbsp;I believe I need to use PROC NLIN to accomplish this, but don't know how to set up the code for the two potential break points. &amp;nbsp;I have attached a dummy data set. &amp;nbsp;Could one of you be so kind as to help walk me through the code for this? &amp;nbsp;I am interested in finding the break point or points, and the adj. r^2.&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;I appreciate your time,&amp;nbsp;&lt;/P&gt;&lt;P&gt;Thank you,&lt;/P&gt;&lt;P&gt;Tim Muhich&lt;/P&gt;</description>
      <pubDate>Mon, 23 Nov 2015 15:18:36 GMT</pubDate>
      <guid>https://communities.sas.com/t5/SAS-Procedures/piecewise-regression/m-p/235996#M55186</guid>
      <dc:creator>tmuhich</dc:creator>
      <dc:date>2015-11-23T15:18:36Z</dc:date>
    </item>
    <item>
      <title>Re: piecewise regression</title>
      <link>https://communities.sas.com/t5/SAS-Procedures/piecewise-regression/m-p/236049#M55191</link>
      <description>&lt;P&gt;There have been several papers written on this topic.&amp;nbsp; You will need one parameter for each location where you think the derivative is discontinuous. One easy-to-read paper is by &lt;A href="http://people.stat.sfu.ca/~cschwarz/Stat-650/Notes/PDFbigbook-SAS/SAS-part018.pdf" target="_self"&gt;Schwarz (2015)&lt;/A&gt;.&amp;nbsp; It is the similar to &lt;A href="http://www.ats.ucla.edu/stat/sas/faq/nlin_optimal_knots.htm" target="_self"&gt;an example from the UCLA web site&lt;/A&gt;. They both include code for PROC NLIN, although the example only has a single "elbow" point where the PL curve changes slope.&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;</description>
      <pubDate>Mon, 23 Nov 2015 18:27:34 GMT</pubDate>
      <guid>https://communities.sas.com/t5/SAS-Procedures/piecewise-regression/m-p/236049#M55191</guid>
      <dc:creator>Rick_SAS</dc:creator>
      <dc:date>2015-11-23T18:27:34Z</dc:date>
    </item>
  </channel>
</rss>

