<?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: How to flag used observations in regression model? in SAS Procedures</title>
    <link>https://communities.sas.com/t5/SAS-Procedures/How-to-flag-used-observations-in-regression-model/m-p/62613#M17806</link>
    <description>if these predictor variables are &lt;BR /&gt;
1 : all numeric&lt;BR /&gt;
and&lt;BR /&gt;
2 : listed in macro variable &amp;amp;predictors&lt;BR /&gt;
data new_dataset ;&lt;BR /&gt;
   set old_dataset ;&lt;BR /&gt;
   if nmiss( of &amp;amp;predictors ) &amp;gt; 0  then delete ;&lt;BR /&gt;
run ;</description>
    <pubDate>Mon, 10 Aug 2009 14:07:14 GMT</pubDate>
    <dc:creator>Peter_C</dc:creator>
    <dc:date>2009-08-10T14:07:14Z</dc:date>
    <item>
      <title>How to flag used observations in regression model?</title>
      <link>https://communities.sas.com/t5/SAS-Procedures/How-to-flag-used-observations-in-regression-model/m-p/62612#M17805</link>
      <description>When I perform a logistic regression model using about 50 predictor variables my sample size decreases from n=18500 to n=7468 due to missing data on some of the variables. I want to create a new dataset that only includes the complete cases (n=7468). Is there an easy way to do this in SAS?</description>
      <pubDate>Sun, 09 Aug 2009 16:03:11 GMT</pubDate>
      <guid>https://communities.sas.com/t5/SAS-Procedures/How-to-flag-used-observations-in-regression-model/m-p/62612#M17805</guid>
      <dc:creator>sjmoussa</dc:creator>
      <dc:date>2009-08-09T16:03:11Z</dc:date>
    </item>
    <item>
      <title>Re: How to flag used observations in regression model?</title>
      <link>https://communities.sas.com/t5/SAS-Procedures/How-to-flag-used-observations-in-regression-model/m-p/62613#M17806</link>
      <description>if these predictor variables are &lt;BR /&gt;
1 : all numeric&lt;BR /&gt;
and&lt;BR /&gt;
2 : listed in macro variable &amp;amp;predictors&lt;BR /&gt;
data new_dataset ;&lt;BR /&gt;
   set old_dataset ;&lt;BR /&gt;
   if nmiss( of &amp;amp;predictors ) &amp;gt; 0  then delete ;&lt;BR /&gt;
run ;</description>
      <pubDate>Mon, 10 Aug 2009 14:07:14 GMT</pubDate>
      <guid>https://communities.sas.com/t5/SAS-Procedures/How-to-flag-used-observations-in-regression-model/m-p/62613#M17806</guid>
      <dc:creator>Peter_C</dc:creator>
      <dc:date>2009-08-10T14:07:14Z</dc:date>
    </item>
    <item>
      <title>Re: How to flag used observations in regression model?</title>
      <link>https://communities.sas.com/t5/SAS-Procedures/How-to-flag-used-observations-in-regression-model/m-p/62614#M17807</link>
      <description>You could output a dataset that includes the predicted risk and then subset on that value being non-missing.</description>
      <pubDate>Mon, 10 Aug 2009 15:52:29 GMT</pubDate>
      <guid>https://communities.sas.com/t5/SAS-Procedures/How-to-flag-used-observations-in-regression-model/m-p/62614#M17807</guid>
      <dc:creator>Doc_Duke</dc:creator>
      <dc:date>2009-08-10T15:52:29Z</dc:date>
    </item>
  </channel>
</rss>

