<?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: SurveyReg: How to run SurveyReg when many dummies are included in the mode? in Statistical Procedures</title>
    <link>https://communities.sas.com/t5/Statistical-Procedures/SurveyReg-How-to-run-SurveyReg-when-many-dummies-are-included-in/m-p/401782#M20950</link>
    <description>&lt;P&gt;Just a comment: PROC SURVEYREG supports the CLASS statement, so your code will probably be easier to read and maintain if you&amp;nbsp;use classification variables instead of using dummy variables.&lt;/P&gt;</description>
    <pubDate>Fri, 06 Oct 2017 14:16:41 GMT</pubDate>
    <dc:creator>Rick_SAS</dc:creator>
    <dc:date>2017-10-06T14:16:41Z</dc:date>
    <item>
      <title>SurveyReg: How to run SurveyReg when many dummies are included in the mode?</title>
      <link>https://communities.sas.com/t5/Statistical-Procedures/SurveyReg-How-to-run-SurveyReg-when-many-dummies-are-included-in/m-p/401193#M20948</link>
      <description>&lt;P&gt;Hi, I tried to run the following SurveyReg model:&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;Proc SurveyReg Data=Data1;&lt;/P&gt;&lt;P&gt;Cluster Year;&lt;/P&gt;&lt;P&gt;Model Y=X1&amp;nbsp; X2&amp;nbsp; X3&amp;nbsp; X4&amp;nbsp; Dummy1-Dummy500;&lt;/P&gt;&lt;P&gt;Ods Output&amp;nbsp;EstimateCoef = MyParmEst;&lt;/P&gt;&lt;P&gt;Run;&amp;nbsp;&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;Dummy1-Dummy500 are included to control for fixed effects.&lt;/P&gt;&lt;P&gt;However,&amp;nbsp;maybe due to the large number of dummies, the SAS log reports that the procedure is stopped due to insufficient memory.&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;If I use Proc Reg, I can use the following code to avoid the problem of insufficient memory:&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;Proc Reg Data=Data1 NoPrint Outest=Data2 Tableout;&lt;BR /&gt;Model Y=X1&amp;nbsp; X2&amp;nbsp; X3&amp;nbsp; Dummy1-Dummy500;&lt;BR /&gt;Run;&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;However, NoPrint is not allowed when Proc SurveyReg is used.&lt;/P&gt;&lt;P&gt;I wonder whether it is possible to have cluster and have many dummies in SAS at the same time,&lt;/P&gt;&lt;P&gt;and whether it is possible to avoid the problem of insufficient memory.&lt;/P&gt;&lt;P&gt;Hope the question is clear.&lt;/P&gt;&lt;P&gt;Thank you so much for any advice.&lt;/P&gt;</description>
      <pubDate>Thu, 05 Oct 2017 06:45:58 GMT</pubDate>
      <guid>https://communities.sas.com/t5/Statistical-Procedures/SurveyReg-How-to-run-SurveyReg-when-many-dummies-are-included-in/m-p/401193#M20948</guid>
      <dc:creator>JoeyHuang</dc:creator>
      <dc:date>2017-10-05T06:45:58Z</dc:date>
    </item>
    <item>
      <title>Re: SurveyReg: How to run SurveyReg when many dummies are included in the mode?</title>
      <link>https://communities.sas.com/t5/Statistical-Procedures/SurveyReg-How-to-run-SurveyReg-when-many-dummies-are-included-in/m-p/401459#M20949</link>
      <description>&lt;P&gt;The memory issue may be building all of the output tables in memory before the ods output can be displayed.&lt;/P&gt;
&lt;P&gt;You might try the ODS Select statement to only select the EstimateCoef table for output before the proc statement.&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;P&gt;I do agree that the lack of an OUTEST data set is a bottleneck and I don't even use 20 variable models.&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;</description>
      <pubDate>Thu, 05 Oct 2017 17:39:44 GMT</pubDate>
      <guid>https://communities.sas.com/t5/Statistical-Procedures/SurveyReg-How-to-run-SurveyReg-when-many-dummies-are-included-in/m-p/401459#M20949</guid>
      <dc:creator>ballardw</dc:creator>
      <dc:date>2017-10-05T17:39:44Z</dc:date>
    </item>
    <item>
      <title>Re: SurveyReg: How to run SurveyReg when many dummies are included in the mode?</title>
      <link>https://communities.sas.com/t5/Statistical-Procedures/SurveyReg-How-to-run-SurveyReg-when-many-dummies-are-included-in/m-p/401782#M20950</link>
      <description>&lt;P&gt;Just a comment: PROC SURVEYREG supports the CLASS statement, so your code will probably be easier to read and maintain if you&amp;nbsp;use classification variables instead of using dummy variables.&lt;/P&gt;</description>
      <pubDate>Fri, 06 Oct 2017 14:16:41 GMT</pubDate>
      <guid>https://communities.sas.com/t5/Statistical-Procedures/SurveyReg-How-to-run-SurveyReg-when-many-dummies-are-included-in/m-p/401782#M20950</guid>
      <dc:creator>Rick_SAS</dc:creator>
      <dc:date>2017-10-06T14:16:41Z</dc:date>
    </item>
    <item>
      <title>Re: SurveyReg: How to run SurveyReg when many dummies are included in the mode?</title>
      <link>https://communities.sas.com/t5/Statistical-Procedures/SurveyReg-How-to-run-SurveyReg-when-many-dummies-are-included-in/m-p/402125#M20966</link>
      <description>&lt;P&gt;Thanks a lot for the suggestion.&lt;/P&gt;&lt;P&gt;I will try it soon.&lt;/P&gt;</description>
      <pubDate>Sat, 07 Oct 2017 23:24:27 GMT</pubDate>
      <guid>https://communities.sas.com/t5/Statistical-Procedures/SurveyReg-How-to-run-SurveyReg-when-many-dummies-are-included-in/m-p/402125#M20966</guid>
      <dc:creator>JoeyHuang</dc:creator>
      <dc:date>2017-10-07T23:24:27Z</dc:date>
    </item>
  </channel>
</rss>

