<?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: questions about calculating marginal effects in SAS Procedures</title>
    <link>https://communities.sas.com/t5/SAS-Procedures/questions-about-calculating-marginal-effects/m-p/46625#M12446</link>
    <description>April,&lt;BR /&gt;
&lt;BR /&gt;
I can't answer your question about differences between SAS and Stata results but, as for whether you need SAS/ETS to calculate marginal effects, take a look at the example comparing qlim and logistic:&lt;BR /&gt;
&lt;BR /&gt;
&lt;A href="http://support.sas.com/kb/25/007.html" target="_blank"&gt;http://support.sas.com/kb/25/007.html&lt;/A&gt;&lt;BR /&gt;
&lt;BR /&gt;
HTH,&lt;BR /&gt;
Art&lt;BR /&gt;
-----------&lt;BR /&gt;
&amp;gt; Hi there,&lt;BR /&gt;
&amp;gt; &lt;BR /&gt;
&amp;gt; I am currently working on a project which requires me&lt;BR /&gt;
&amp;gt; to calculate marginal effects. I choose probit model&lt;BR /&gt;
&amp;gt; because most variables are categorical variables. I&lt;BR /&gt;
&amp;gt; also created dummy variables for all the categorical&lt;BR /&gt;
&amp;gt; variables. However, it seems the result is not&lt;BR /&gt;
&amp;gt; good(different from the results generated by&lt;BR /&gt;
&amp;gt; collegues using stata). I do not think there should&lt;BR /&gt;
&amp;gt; be any differences. &lt;BR /&gt;
&amp;gt; &lt;BR /&gt;
&amp;gt; Basically, I am using doing it in this way:&lt;BR /&gt;
&amp;gt;    proc qlim data=greenedata;&lt;BR /&gt;
&amp;gt;    model grade = gpa tuce psi / discrete(d=probit);&lt;BR /&gt;
&amp;gt;    output out=outme marginal;&lt;BR /&gt;
&amp;gt; run;&lt;BR /&gt;
&amp;gt;    quit;&lt;BR /&gt;
&amp;gt; s the function of calculating marginal effects only&lt;BR /&gt;
&amp;gt; available in SAS/ETS but not in SAS base?&lt;BR /&gt;
&amp;gt; &lt;BR /&gt;
&amp;gt; Thank you guys!&lt;BR /&gt;
&amp;gt; &lt;BR /&gt;
&amp;gt; April</description>
    <pubDate>Sat, 10 Jul 2010 20:25:51 GMT</pubDate>
    <dc:creator>art297</dc:creator>
    <dc:date>2010-07-10T20:25:51Z</dc:date>
    <item>
      <title>questions about calculating marginal effects</title>
      <link>https://communities.sas.com/t5/SAS-Procedures/questions-about-calculating-marginal-effects/m-p/46624#M12445</link>
      <description>Hi there,&lt;BR /&gt;
&lt;BR /&gt;
I am currently working on a project which requires me to calculate marginal effects. I choose probit model because most variables are categorical variables. I also created dummy variables for all the categorical variables. However, it seems the result is not good(different from the results generated by collegues using stata). I do not think there should be any differences. &lt;BR /&gt;
&lt;BR /&gt;
Basically, I am using doing it in this way:&lt;BR /&gt;
   proc qlim data=greenedata;&lt;BR /&gt;
      model grade = gpa tuce psi / discrete(d=probit);&lt;BR /&gt;
      output out=outme marginal;&lt;BR /&gt;
   run;&lt;BR /&gt;
   quit;&lt;BR /&gt;
&lt;BR /&gt;
Is the function of calculating marginal effects only available in SAS/ETS but not in SAS base?&lt;BR /&gt;
&lt;BR /&gt;
Thank you guys!&lt;BR /&gt;
&lt;BR /&gt;
April</description>
      <pubDate>Fri, 09 Jul 2010 19:48:38 GMT</pubDate>
      <guid>https://communities.sas.com/t5/SAS-Procedures/questions-about-calculating-marginal-effects/m-p/46624#M12445</guid>
      <dc:creator>applebee</dc:creator>
      <dc:date>2010-07-09T19:48:38Z</dc:date>
    </item>
    <item>
      <title>Re: questions about calculating marginal effects</title>
      <link>https://communities.sas.com/t5/SAS-Procedures/questions-about-calculating-marginal-effects/m-p/46625#M12446</link>
      <description>April,&lt;BR /&gt;
&lt;BR /&gt;
I can't answer your question about differences between SAS and Stata results but, as for whether you need SAS/ETS to calculate marginal effects, take a look at the example comparing qlim and logistic:&lt;BR /&gt;
&lt;BR /&gt;
&lt;A href="http://support.sas.com/kb/25/007.html" target="_blank"&gt;http://support.sas.com/kb/25/007.html&lt;/A&gt;&lt;BR /&gt;
&lt;BR /&gt;
HTH,&lt;BR /&gt;
Art&lt;BR /&gt;
-----------&lt;BR /&gt;
&amp;gt; Hi there,&lt;BR /&gt;
&amp;gt; &lt;BR /&gt;
&amp;gt; I am currently working on a project which requires me&lt;BR /&gt;
&amp;gt; to calculate marginal effects. I choose probit model&lt;BR /&gt;
&amp;gt; because most variables are categorical variables. I&lt;BR /&gt;
&amp;gt; also created dummy variables for all the categorical&lt;BR /&gt;
&amp;gt; variables. However, it seems the result is not&lt;BR /&gt;
&amp;gt; good(different from the results generated by&lt;BR /&gt;
&amp;gt; collegues using stata). I do not think there should&lt;BR /&gt;
&amp;gt; be any differences. &lt;BR /&gt;
&amp;gt; &lt;BR /&gt;
&amp;gt; Basically, I am using doing it in this way:&lt;BR /&gt;
&amp;gt;    proc qlim data=greenedata;&lt;BR /&gt;
&amp;gt;    model grade = gpa tuce psi / discrete(d=probit);&lt;BR /&gt;
&amp;gt;    output out=outme marginal;&lt;BR /&gt;
&amp;gt; run;&lt;BR /&gt;
&amp;gt;    quit;&lt;BR /&gt;
&amp;gt; s the function of calculating marginal effects only&lt;BR /&gt;
&amp;gt; available in SAS/ETS but not in SAS base?&lt;BR /&gt;
&amp;gt; &lt;BR /&gt;
&amp;gt; Thank you guys!&lt;BR /&gt;
&amp;gt; &lt;BR /&gt;
&amp;gt; April</description>
      <pubDate>Sat, 10 Jul 2010 20:25:51 GMT</pubDate>
      <guid>https://communities.sas.com/t5/SAS-Procedures/questions-about-calculating-marginal-effects/m-p/46625#M12446</guid>
      <dc:creator>art297</dc:creator>
      <dc:date>2010-07-10T20:25:51Z</dc:date>
    </item>
  </channel>
</rss>

