<?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: proc glimmix control for within- and between-hospital correlations in Statistical Procedures</title>
    <link>https://communities.sas.com/t5/Statistical-Procedures/proc-glimmix-control-for-within-and-between-hospital/m-p/560316#M27737</link>
    <description>&lt;P&gt;I have never heard of the concept of "controlling for correlations ". What does it mean? Is this something commonly done with this type of model?&amp;nbsp;&lt;/P&gt;</description>
    <pubDate>Tue, 21 May 2019 00:20:37 GMT</pubDate>
    <dc:creator>PaigeMiller</dc:creator>
    <dc:date>2019-05-21T00:20:37Z</dc:date>
    <item>
      <title>proc glimmix control for within- and between-hospital correlations</title>
      <link>https://communities.sas.com/t5/Statistical-Procedures/proc-glimmix-control-for-within-and-between-hospital/m-p/560204#M27731</link>
      <description>&lt;P&gt;Hello,&lt;/P&gt;&lt;P&gt;I have a dataset of ~25000 patients from ~1300 hospitals.&amp;nbsp; I would like to calculate the odds of receiving one of two treatments, then obtain the probability of treatment for each patient (for propensity score adjustment).&amp;nbsp; 20 patients were selected from each hospital, with treatment=1 oversampled, so the data has been weighted (weight variable='selweight').&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;I would like to control for correlations between patients at the same hospitals , and let the correlations vary by hospital.&amp;nbsp; I have tried proc glimmix, with treatment='x', hospital code='oldfaccode' and patient id='puf_id', and a number of covariates, with an exchangeable correlation matrix:&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;PRE&gt;&lt;CODE class=" language-sas"&gt;proc glimmix data=raw_data;
class

oldfaccode&amp;nbsp;puf_id&amp;nbsp;dxyr (ref='2008')&amp;nbsp;facility_type_cd (ref='2')&amp;nbsp;facloc(ref='Northeast')&amp;nbsp;&amp;nbsp;RACEcat (ref='White') hispanic (ref='0')
MED_INC_QUAR_12 (ref='1') NO_HSD_QUAR_12 (ref='1') metro13 (ref='0')&amp;nbsp;insured (ref='1')&amp;nbsp;charlson(ref='1')
er1 (ref='Negative/normal, within normal limits') pr1 (ref='Negative/normal, within normal limits') grade1 (ref="Grade I")
comedonecrosis1(ref='1) Present') detect_dcis1 (ref='1) Mammogram')


MODEL x= age dxyr facility_type_cd&amp;nbsp;facloc RACEcat hispanic MED_INC_QUAR_12 NO_HSD_QUAR_12 charlson
metro13 insured er1 pr1&amp;nbsp;grade1 detect_dcis1&amp;nbsp;comedonecrosis1 /solution ;
subject=puf_id(oldfaccode) type=cs ;
random intercept/subject=oldfaccode type=cs; 
weight selweight;
run;

&lt;/CODE&gt;&lt;/PRE&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;In order to let the correlations vary between hospitals, I am using the statement&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;PRE&gt;&lt;CODE class=" language-sas"&gt;random intercept/subject=puf_id(oldfaccode) type=cs&lt;/CODE&gt;&lt;/PRE&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;Is this correct?&amp;nbsp; I'm not even sure if I am using the terminology correctly.&amp;nbsp;&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;Additionally, how do I output the predicted probabilities?&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;Thank you so much for any help!&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;</description>
      <pubDate>Mon, 20 May 2019 15:55:52 GMT</pubDate>
      <guid>https://communities.sas.com/t5/Statistical-Procedures/proc-glimmix-control-for-within-and-between-hospital/m-p/560204#M27731</guid>
      <dc:creator>laura114</dc:creator>
      <dc:date>2019-05-20T15:55:52Z</dc:date>
    </item>
    <item>
      <title>Re: proc glimmix control for within- and between-hospital correlations</title>
      <link>https://communities.sas.com/t5/Statistical-Procedures/proc-glimmix-control-for-within-and-between-hospital/m-p/560316#M27737</link>
      <description>&lt;P&gt;I have never heard of the concept of "controlling for correlations ". What does it mean? Is this something commonly done with this type of model?&amp;nbsp;&lt;/P&gt;</description>
      <pubDate>Tue, 21 May 2019 00:20:37 GMT</pubDate>
      <guid>https://communities.sas.com/t5/Statistical-Procedures/proc-glimmix-control-for-within-and-between-hospital/m-p/560316#M27737</guid>
      <dc:creator>PaigeMiller</dc:creator>
      <dc:date>2019-05-21T00:20:37Z</dc:date>
    </item>
  </channel>
</rss>

