<?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 How to model or represent mathematically a periodic sigmoid like function in Statistical Procedures</title>
    <link>https://communities.sas.com/t5/Statistical-Procedures/How-to-model-or-represent-mathematically-a-periodic-sigmoid-like/m-p/618779#M29788</link>
    <description>For an sales incentive system I'd like to model a sigmoid function that repeats periodically and increases thereby by a step function.&lt;BR /&gt;Any idea?&lt;BR /&gt;An approximation is okay for me as I'm aware of the fact that the sigmoid input ranges from minus infinity to plus infinity and that the function is convergent towards 0 and 1.</description>
    <pubDate>Tue, 21 Jan 2020 07:05:56 GMT</pubDate>
    <dc:creator>acordes</dc:creator>
    <dc:date>2020-01-21T07:05:56Z</dc:date>
    <item>
      <title>How to model or represent mathematically a periodic sigmoid like function</title>
      <link>https://communities.sas.com/t5/Statistical-Procedures/How-to-model-or-represent-mathematically-a-periodic-sigmoid-like/m-p/618779#M29788</link>
      <description>For an sales incentive system I'd like to model a sigmoid function that repeats periodically and increases thereby by a step function.&lt;BR /&gt;Any idea?&lt;BR /&gt;An approximation is okay for me as I'm aware of the fact that the sigmoid input ranges from minus infinity to plus infinity and that the function is convergent towards 0 and 1.</description>
      <pubDate>Tue, 21 Jan 2020 07:05:56 GMT</pubDate>
      <guid>https://communities.sas.com/t5/Statistical-Procedures/How-to-model-or-represent-mathematically-a-periodic-sigmoid-like/m-p/618779#M29788</guid>
      <dc:creator>acordes</dc:creator>
      <dc:date>2020-01-21T07:05:56Z</dc:date>
    </item>
    <item>
      <title>Re: How to model or represent mathematically a periodic sigmoid like function</title>
      <link>https://communities.sas.com/t5/Statistical-Procedures/How-to-model-or-represent-mathematically-a-periodic-sigmoid-like/m-p/618853#M29790</link>
      <description>&lt;P&gt;&lt;SPAN&gt;I guess you mean that it is a sigmoid on each periodic domain and overall it is a monotonic nondecreasing function.&lt;/SPAN&gt;&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;P&gt;The main thing you need to do is identify a base function and the domain of periodicity.&amp;nbsp; I have chosen the base function to be&amp;nbsp;&lt;/P&gt;
&lt;P&gt;f(x) = (1 - cos(pi*x)) / 2&amp;nbsp; for x in [0, 1]&lt;/P&gt;
&lt;P&gt;which is a monotonic function that has the range [0, 1].&lt;/P&gt;
&lt;P&gt;You can then extend the base function by adding a step function to it.&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;P&gt;One step function is s(x) = floor(x).&amp;nbsp;&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;PRE&gt;&lt;CODE class=" language-sas"&gt;/* The base function has domain [0, 1] and also range [0, 1].
   The base function is
   f(x) = (1 - cos(pi*x)) /2
*/
data PeriodicSigmoid;
   pi = constant('pi');
   do x = 1 to 6 by 0.01;
      z = x - floor(x);     /* z is always in [0,1] */
      y = floor(x) + (1 - cos(pi*z)) /2;  /* add step function to base function */
      output;
   end;
run;

proc sgplot data=PeriodicSigmoid;
   series x=x y=y;
   xaxis grid;
run;&lt;/CODE&gt;&lt;/PRE&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;</description>
      <pubDate>Tue, 21 Jan 2020 13:25:48 GMT</pubDate>
      <guid>https://communities.sas.com/t5/Statistical-Procedures/How-to-model-or-represent-mathematically-a-periodic-sigmoid-like/m-p/618853#M29790</guid>
      <dc:creator>Rick_SAS</dc:creator>
      <dc:date>2020-01-21T13:25:48Z</dc:date>
    </item>
  </channel>
</rss>

