<?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: INITIAL option and BY statements in GENMOD procedure in Statistical Procedures</title>
    <link>https://communities.sas.com/t5/Statistical-Procedures/INTERCEPT-option-and-BY-statements-in-GENMOD-procedure/m-p/48655#M2160</link>
    <description>Good question!  It does not appear to me that it is possible to initialize the intercept for any but the first by group - unless you specify the NOINT option.  Specifying an intercept along with the NOINT option would fix an intercept at the specified value (which, I believe, is probably not what you want).&lt;BR /&gt;
&lt;BR /&gt;
I would report this to SI as a bug and see what they say.</description>
    <pubDate>Fri, 29 Jan 2010 20:08:54 GMT</pubDate>
    <dc:creator>Dale</dc:creator>
    <dc:date>2010-01-29T20:08:54Z</dc:date>
    <item>
      <title>INTERCEPT option and BY statements in GENMOD procedure</title>
      <link>https://communities.sas.com/t5/Statistical-Procedures/INTERCEPT-option-and-BY-statements-in-GENMOD-procedure/m-p/48654#M2159</link>
      <description>I'm using the BY statement to have split calculations for various groups in the same dataset, but when I specify initial values for the intercept estimate in PROC GENMOD (INTERCEPT option to the MODEL statement), only the first of the BY-groups uses the initial value. Is there any way to give an initial value for each BY-group?&lt;BR /&gt;
&lt;BR /&gt;
Edit: Confused INITIAL and INTERCEPT options in original post.

Message was edited by: T</description>
      <pubDate>Fri, 29 Jan 2010 12:41:56 GMT</pubDate>
      <guid>https://communities.sas.com/t5/Statistical-Procedures/INTERCEPT-option-and-BY-statements-in-GENMOD-procedure/m-p/48654#M2159</guid>
      <dc:creator>T</dc:creator>
      <dc:date>2010-01-29T12:41:56Z</dc:date>
    </item>
    <item>
      <title>Re: INITIAL option and BY statements in GENMOD procedure</title>
      <link>https://communities.sas.com/t5/Statistical-Procedures/INTERCEPT-option-and-BY-statements-in-GENMOD-procedure/m-p/48655#M2160</link>
      <description>Good question!  It does not appear to me that it is possible to initialize the intercept for any but the first by group - unless you specify the NOINT option.  Specifying an intercept along with the NOINT option would fix an intercept at the specified value (which, I believe, is probably not what you want).&lt;BR /&gt;
&lt;BR /&gt;
I would report this to SI as a bug and see what they say.</description>
      <pubDate>Fri, 29 Jan 2010 20:08:54 GMT</pubDate>
      <guid>https://communities.sas.com/t5/Statistical-Procedures/INTERCEPT-option-and-BY-statements-in-GENMOD-procedure/m-p/48655#M2160</guid>
      <dc:creator>Dale</dc:creator>
      <dc:date>2010-01-29T20:08:54Z</dc:date>
    </item>
    <item>
      <title>Re: INITIAL option and BY statements in GENMOD procedure</title>
      <link>https://communities.sas.com/t5/Statistical-Procedures/INTERCEPT-option-and-BY-statements-in-GENMOD-procedure/m-p/48656#M2161</link>
      <description>I've reported to the SAS Support now, so we'll see if they have a solution. Thanks for your reply.</description>
      <pubDate>Wed, 03 Feb 2010 10:56:18 GMT</pubDate>
      <guid>https://communities.sas.com/t5/Statistical-Procedures/INTERCEPT-option-and-BY-statements-in-GENMOD-procedure/m-p/48656#M2161</guid>
      <dc:creator>T</dc:creator>
      <dc:date>2010-02-03T10:56:18Z</dc:date>
    </item>
    <item>
      <title>Re: INITIAL option and BY statements in GENMOD procedure</title>
      <link>https://communities.sas.com/t5/Statistical-Procedures/INTERCEPT-option-and-BY-statements-in-GENMOD-procedure/m-p/48657#M2162</link>
      <description>Hi again,&lt;BR /&gt;
&lt;BR /&gt;
I had a reply from the SAS Support. Apparently this is a known limitation with GENMOD, which they hope to fix in the next version.&lt;BR /&gt;
&lt;BR /&gt;
Until then, I guess the WHERE statement is an acceptable work-around.</description>
      <pubDate>Mon, 08 Feb 2010 15:14:40 GMT</pubDate>
      <guid>https://communities.sas.com/t5/Statistical-Procedures/INTERCEPT-option-and-BY-statements-in-GENMOD-procedure/m-p/48657#M2162</guid>
      <dc:creator>T</dc:creator>
      <dc:date>2010-02-08T15:14:40Z</dc:date>
    </item>
  </channel>
</rss>

