<?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 linear growth-curve modeling using Proc Mixed in Statistical Procedures</title>
    <link>https://communities.sas.com/t5/Statistical-Procedures/Piecewise-linear-growth-curve-modeling-using-Proc-Mixed/m-p/409823#M21396</link>
    <description>&lt;P&gt;You mentioned splines, but your&amp;nbsp;code does not appear to use splines. When you use the EFFECT statement to construct the spline, put a knot at time=4. That will enable you to create a piecewise linear model. See the second example in the article &lt;A href="https://blogs.sas.com/content/iml/2017/04/05/nonsmooth-models-spline-effects.html" target="_self"&gt;"Nonsmooth models and spline effects."&lt;/A&gt;&lt;/P&gt;</description>
    <pubDate>Thu, 02 Nov 2017 14:01:30 GMT</pubDate>
    <dc:creator>Rick_SAS</dc:creator>
    <dc:date>2017-11-02T14:01:30Z</dc:date>
    <item>
      <title>Piecewise linear growth-curve modeling using Proc Mixed</title>
      <link>https://communities.sas.com/t5/Statistical-Procedures/Piecewise-linear-growth-curve-modeling-using-Proc-Mixed/m-p/409613#M21376</link>
      <description>&lt;P&gt;Hello,&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;I am trying to model blood pressure growth trajectories&amp;nbsp; across two distinct periods (reactivity and recovery from a stressor). I am looking to examine rates of linear growth&amp;nbsp;for levels of&amp;nbsp;bp for each person&amp;nbsp;within each period. I also include person-level predictors.&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;I am currently modeling blood pressure as a function of each time point. However, there are 8 time points (4 during the reactivity phase and 4 during the recovery phase), and I would like to divide time into two periods, before minute 4 and after minute 4.&lt;/P&gt;&lt;P&gt;Here is my SAS code modeling each time point (I use SAS 9.4):&lt;/P&gt;&lt;PRE&gt;&lt;CODE class=" language-sas"&gt;proc mixed data=third;
class condition time;
model systolic =  time|condition;
repeated time / sub=id type=un;
lsmeans time|condition;
run; &lt;/CODE&gt;&lt;/PRE&gt;&lt;P&gt;How can I create a spline model where I can get two separate coefficients (one before time=4 and one after time=4)?&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;Thank you!&lt;/P&gt;</description>
      <pubDate>Wed, 01 Nov 2017 19:46:45 GMT</pubDate>
      <guid>https://communities.sas.com/t5/Statistical-Procedures/Piecewise-linear-growth-curve-modeling-using-Proc-Mixed/m-p/409613#M21376</guid>
      <dc:creator>kleger</dc:creator>
      <dc:date>2017-11-01T19:46:45Z</dc:date>
    </item>
    <item>
      <title>Re: Piecewise linear growth-curve modeling using Proc Mixed</title>
      <link>https://communities.sas.com/t5/Statistical-Procedures/Piecewise-linear-growth-curve-modeling-using-Proc-Mixed/m-p/409682#M21382</link>
      <description>&lt;P&gt;Change my time of 12 to your time of 4.&lt;/P&gt;
&lt;PRE&gt;&lt;CODE class=" language-sas"&gt;data x;
   set sashelp.class(rename=(age=time));
   time1 = (time &amp;lt;= 12) * time;
   time2 = (time &amp;gt;  12) * time;
   run;&lt;/CODE&gt;&lt;/PRE&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;</description>
      <pubDate>Thu, 02 Nov 2017 00:02:52 GMT</pubDate>
      <guid>https://communities.sas.com/t5/Statistical-Procedures/Piecewise-linear-growth-curve-modeling-using-Proc-Mixed/m-p/409682#M21382</guid>
      <dc:creator>WarrenKuhfeld</dc:creator>
      <dc:date>2017-11-02T00:02:52Z</dc:date>
    </item>
    <item>
      <title>Re: Piecewise linear growth-curve modeling using Proc Mixed</title>
      <link>https://communities.sas.com/t5/Statistical-Procedures/Piecewise-linear-growth-curve-modeling-using-Proc-Mixed/m-p/409823#M21396</link>
      <description>&lt;P&gt;You mentioned splines, but your&amp;nbsp;code does not appear to use splines. When you use the EFFECT statement to construct the spline, put a knot at time=4. That will enable you to create a piecewise linear model. See the second example in the article &lt;A href="https://blogs.sas.com/content/iml/2017/04/05/nonsmooth-models-spline-effects.html" target="_self"&gt;"Nonsmooth models and spline effects."&lt;/A&gt;&lt;/P&gt;</description>
      <pubDate>Thu, 02 Nov 2017 14:01:30 GMT</pubDate>
      <guid>https://communities.sas.com/t5/Statistical-Procedures/Piecewise-linear-growth-curve-modeling-using-Proc-Mixed/m-p/409823#M21396</guid>
      <dc:creator>Rick_SAS</dc:creator>
      <dc:date>2017-11-02T14:01:30Z</dc:date>
    </item>
    <item>
      <title>Re: Piecewise linear growth-curve modeling using Proc Mixed</title>
      <link>https://communities.sas.com/t5/Statistical-Procedures/Piecewise-linear-growth-curve-modeling-using-Proc-Mixed/m-p/409960#M21408</link>
      <description>&lt;P&gt;Thank you, Rick! This was very helpful.&lt;/P&gt;</description>
      <pubDate>Thu, 02 Nov 2017 18:21:32 GMT</pubDate>
      <guid>https://communities.sas.com/t5/Statistical-Procedures/Piecewise-linear-growth-curve-modeling-using-Proc-Mixed/m-p/409960#M21408</guid>
      <dc:creator>kleger</dc:creator>
      <dc:date>2017-11-02T18:21:32Z</dc:date>
    </item>
  </channel>
</rss>

