<?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 proc mixed repeated output help in Statistical Procedures</title>
    <link>https://communities.sas.com/t5/Statistical-Procedures/proc-mixed-repeated-output-help/m-p/70960#M3442</link>
    <description>Hello everyone,&lt;BR /&gt;
&lt;BR /&gt;
Suppose I have a simple repeated measures model:&lt;BR /&gt;
&lt;BR /&gt;
proc mixed;&lt;BR /&gt;
class id group time;&lt;BR /&gt;
model y=group time /s;&lt;BR /&gt;
repeated time/ type=un subject=id &lt;B&gt;rci=1,2,3&lt;/B&gt;;&lt;BR /&gt;
ods output InvCholR(match_all)=test1&lt;BR /&gt;
run;&lt;BR /&gt;
&lt;BR /&gt;
the model itself is not important in this case. My question involves the bolded part. I want to save the InvCholR matrices for each subject that was used in the model and the ods output command will take care of that. My problem here is that I have over 60 subjects and not all have full data thus not every subject is being used.&lt;BR /&gt;
&lt;BR /&gt;
The only way I can see which subjects where used is to look at the Class Level Information and then manually sit there and type rci=1,2,5,7,8,12,14,.....&lt;BR /&gt;
&lt;BR /&gt;
Does anyone know of a way to tell the rci option to use all the subjects used? That way I can say rci=match_all (or something of that sort) and it will give me the rci of all subjects?&lt;BR /&gt;
&lt;BR /&gt;
Cheers&lt;BR /&gt;
George</description>
    <pubDate>Thu, 09 Sep 2010 06:50:11 GMT</pubDate>
    <dc:creator>trekvana</dc:creator>
    <dc:date>2010-09-09T06:50:11Z</dc:date>
    <item>
      <title>proc mixed repeated output help</title>
      <link>https://communities.sas.com/t5/Statistical-Procedures/proc-mixed-repeated-output-help/m-p/70960#M3442</link>
      <description>Hello everyone,&lt;BR /&gt;
&lt;BR /&gt;
Suppose I have a simple repeated measures model:&lt;BR /&gt;
&lt;BR /&gt;
proc mixed;&lt;BR /&gt;
class id group time;&lt;BR /&gt;
model y=group time /s;&lt;BR /&gt;
repeated time/ type=un subject=id &lt;B&gt;rci=1,2,3&lt;/B&gt;;&lt;BR /&gt;
ods output InvCholR(match_all)=test1&lt;BR /&gt;
run;&lt;BR /&gt;
&lt;BR /&gt;
the model itself is not important in this case. My question involves the bolded part. I want to save the InvCholR matrices for each subject that was used in the model and the ods output command will take care of that. My problem here is that I have over 60 subjects and not all have full data thus not every subject is being used.&lt;BR /&gt;
&lt;BR /&gt;
The only way I can see which subjects where used is to look at the Class Level Information and then manually sit there and type rci=1,2,5,7,8,12,14,.....&lt;BR /&gt;
&lt;BR /&gt;
Does anyone know of a way to tell the rci option to use all the subjects used? That way I can say rci=match_all (or something of that sort) and it will give me the rci of all subjects?&lt;BR /&gt;
&lt;BR /&gt;
Cheers&lt;BR /&gt;
George</description>
      <pubDate>Thu, 09 Sep 2010 06:50:11 GMT</pubDate>
      <guid>https://communities.sas.com/t5/Statistical-Procedures/proc-mixed-repeated-output-help/m-p/70960#M3442</guid>
      <dc:creator>trekvana</dc:creator>
      <dc:date>2010-09-09T06:50:11Z</dc:date>
    </item>
    <item>
      <title>Re: proc mixed repeated output help</title>
      <link>https://communities.sas.com/t5/Statistical-Procedures/proc-mixed-repeated-output-help/m-p/70961#M3443</link>
      <description>First of all, I believe that the RCI option takes an ordered subject number with the order value corresponding to ordered ID among the subjects who are used to fit the model.  I believe that if you specify more "subjects" to the RCI option than there are subjects employed in the analysis, that the MIXED procedure will not have a problem with the excess subject count.  So, if you would have at most 100 subjects - but possibly fewer subjects in some analyses - then you should be able to specify&lt;BR /&gt;
&lt;BR /&gt;
proc mixed;&lt;BR /&gt;
class id group time;&lt;BR /&gt;
model y=group time /s;&lt;BR /&gt;
repeated time/ type=un subject=id rci=1 to 100;&lt;BR /&gt;
ods output InvCholR(match_all)=test1&lt;BR /&gt;
run;&lt;BR /&gt;
&lt;BR /&gt;
Try that and report whether that approach will work.</description>
      <pubDate>Thu, 09 Sep 2010 19:17:32 GMT</pubDate>
      <guid>https://communities.sas.com/t5/Statistical-Procedures/proc-mixed-repeated-output-help/m-p/70961#M3443</guid>
      <dc:creator>Dale</dc:creator>
      <dc:date>2010-09-09T19:17:32Z</dc:date>
    </item>
  </channel>
</rss>

