<?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: help with coding in SAS Health and Life Sciences</title>
    <link>https://communities.sas.com/t5/SAS-Health-and-Life-Sciences/help-with-coding/m-p/2696#M211</link>
    <description>Thanks very much!</description>
    <pubDate>Wed, 04 Apr 2007 18:00:37 GMT</pubDate>
    <dc:creator>deleted_user</dc:creator>
    <dc:date>2007-04-04T18:00:37Z</dc:date>
    <item>
      <title>help with coding</title>
      <link>https://communities.sas.com/t5/SAS-Health-and-Life-Sciences/help-with-coding/m-p/2694#M209</link>
      <description>Hello - &lt;BR /&gt;
I am using a macro for proc logistic and would like to output results (OR, CI, pvalue) into table. Currently I am only able to output the beta estimates with the code I have and am not sure how to specify other statistics. &lt;BR /&gt;
&lt;BR /&gt;
    proc logistic data=XYZ outest=_est&amp;amp;k;&lt;BR /&gt;
&lt;BR /&gt;
The problem is with the outest but I don't know what other options work here. &lt;BR /&gt;
Any thoughts? &lt;BR /&gt;
&lt;BR /&gt;
Thanks in advance.</description>
      <pubDate>Tue, 03 Apr 2007 19:18:39 GMT</pubDate>
      <guid>https://communities.sas.com/t5/SAS-Health-and-Life-Sciences/help-with-coding/m-p/2694#M209</guid>
      <dc:creator>deleted_user</dc:creator>
      <dc:date>2007-04-03T19:18:39Z</dc:date>
    </item>
    <item>
      <title>Re: help with coding</title>
      <link>https://communities.sas.com/t5/SAS-Health-and-Life-Sciences/help-with-coding/m-p/2695#M210</link>
      <description>I don't know much about Proc Logistic, but maybe I can help.&lt;BR /&gt;
&lt;BR /&gt;
Found this on the SAS site samples section for Proc Logistic:&lt;BR /&gt;
"out=  Names the output data set to contain the crossvalidated betas (named _CVB0 - _CVBn, where n is the number of explanatory variables and _CVB0 is the crossvalidated intercept), XBETAs, predicted probabilities, and predicted levels. If not specified, the data set is named CVOUT." &lt;BR /&gt;
&lt;BR /&gt;
You have an output dataset containing the information you need, so you can export it out to Excel using code like this:&lt;BR /&gt;
&lt;BR /&gt;
proc export data=CVOUT&lt;BR /&gt;
              outfile="PathName\WorkBookName.xls"&lt;BR /&gt;
              dbms=Excel2000 replace;&lt;BR /&gt;
run;&lt;BR /&gt;
&lt;BR /&gt;
Good luck.</description>
      <pubDate>Tue, 03 Apr 2007 21:47:24 GMT</pubDate>
      <guid>https://communities.sas.com/t5/SAS-Health-and-Life-Sciences/help-with-coding/m-p/2695#M210</guid>
      <dc:creator>Sheri</dc:creator>
      <dc:date>2007-04-03T21:47:24Z</dc:date>
    </item>
    <item>
      <title>Re: help with coding</title>
      <link>https://communities.sas.com/t5/SAS-Health-and-Life-Sciences/help-with-coding/m-p/2696#M211</link>
      <description>Thanks very much!</description>
      <pubDate>Wed, 04 Apr 2007 18:00:37 GMT</pubDate>
      <guid>https://communities.sas.com/t5/SAS-Health-and-Life-Sciences/help-with-coding/m-p/2696#M211</guid>
      <dc:creator>deleted_user</dc:creator>
      <dc:date>2007-04-04T18:00:37Z</dc:date>
    </item>
    <item>
      <title>Re: help with coding</title>
      <link>https://communities.sas.com/t5/SAS-Health-and-Life-Sciences/help-with-coding/m-p/2697#M212</link>
      <description>With a lot of statistical procedures, you can recover infos that are displayed but not available through OUT something options : you just have to use the ODS OUTPUT statement.&lt;BR /&gt;
In your case, something like :&lt;BR /&gt;
&lt;BR /&gt;
ODS OUTPUT parameterEstimates = work.coefficients ;&lt;BR /&gt;
PROC LOGISTIC DATA = xyz ;&lt;BR /&gt;
etc.&lt;BR /&gt;
&lt;BR /&gt;
The trick is to know what is the object name (here : parameterEstimates) that you need. There are different methods :&lt;BR /&gt;
- in the Results windows, find the correct entry, right-click on it and chose properties (it is displayed in a new window and called NAME)&lt;BR /&gt;
- run your program once, with&lt;BR /&gt;
ODS TRACE ON / LISTING ;&lt;BR /&gt;
at the beginning, and &lt;BR /&gt;
ODS TRACE OFF ;&lt;BR /&gt;
at the end.&lt;BR /&gt;
In the Output window, you will have the same informations as above, but in plain text that you can copy and paste.&lt;BR /&gt;
- in the SAS documentation, your will have a "Details" section for each statistical procedure. You will find in this section a "ODS TABLE NAMES" part, which lists all the objects that you can get with the ODS OUTPUT syntax.&lt;BR /&gt;
&lt;BR /&gt;
One last thing about that : place the ODS OUTPUT statement at the line JUST BEFORE the PROC statement. If you type something between the two (even just a TITLE), the dataset will not be created.</description>
      <pubDate>Tue, 24 Apr 2007 12:50:39 GMT</pubDate>
      <guid>https://communities.sas.com/t5/SAS-Health-and-Life-Sciences/help-with-coding/m-p/2697#M212</guid>
      <dc:creator>Olivier</dc:creator>
      <dc:date>2007-04-24T12:50:39Z</dc:date>
    </item>
  </channel>
</rss>

