<?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 Conditional logistic regression using proc logistic or Proc genmod ? in Statistical Procedures</title>
    <link>https://communities.sas.com/t5/Statistical-Procedures/Conditional-logistic-regression-using-proc-logistic-or-Proc/m-p/205164#M11030</link>
    <description>&lt;HTML&gt;&lt;HEAD&gt;&lt;/HEAD&gt;&lt;BODY&gt;&lt;P&gt;Hello~ &lt;/P&gt;&lt;P&gt;I'm trying to estimate the Odds ratio of a treatment after adjusting confounding factors in a 1:2 matched data sets (ex file in the attachement)&lt;/P&gt;&lt;P&gt;Due to the dependence between these data, I'm using conditional logistic regression as statistical method.&lt;/P&gt;&lt;P&gt;PROC Logistic &amp;amp; PROC GENMOD all seems able to deal with matched data well but reported differently.&lt;BR /&gt;I'm wondering what is the difference between proc logistic&amp;nbsp; &amp;amp; proc genmod for dealing with matched data&lt;BR /&gt;and which would be better or more accurate ? .&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt; ## ex data set:&lt;/P&gt;&lt;P&gt;&lt;A href="http://https://www.dropbox.com/s/k3b4yglsofsr4u4/ex.sas7bdat?dl=0"&gt;https://www.dropbox.com/s/k3b4yglsofsr4u4/ex.sas7bdat?dl=0&lt;/A&gt;&lt;/P&gt;&lt;P&gt;Treatment option: Tx; Outcome: Outcome;&amp;nbsp; Confounding factors: B1, C1, B1*Tx;&lt;/P&gt;&lt;TABLE border="0" cellpadding="0" cellspacing="0" style="width: 417px;"&gt;&lt;TBODY&gt;&lt;TR&gt;&lt;TD height="20" width="97"&gt;MATCH_ID&lt;/TD&gt;&lt;TD width="64"&gt;C1&lt;/TD&gt;&lt;TD width="64"&gt;B1&lt;/TD&gt;&lt;TD width="64"&gt;Tx&lt;/TD&gt;&lt;TD width="64"&gt;OUTCOME&lt;/TD&gt;&lt;TD width="64"&gt;STR&lt;/TD&gt;&lt;/TR&gt;&lt;TR&gt;&lt;TD height="20"&gt;0023&lt;/TD&gt;&lt;TD align="right" class="xl63"&gt;78&lt;/TD&gt;&lt;TD align="right" class="xl63"&gt;1&lt;/TD&gt;&lt;TD align="right" class="xl63"&gt;0&lt;/TD&gt;&lt;TD align="right" class="xl63"&gt;0&lt;/TD&gt;&lt;TD align="right" class="xl63"&gt;1&lt;/TD&gt;&lt;/TR&gt;&lt;TR&gt;&lt;TD height="20"&gt;0023&lt;/TD&gt;&lt;TD align="right" class="xl63"&gt;64&lt;/TD&gt;&lt;TD align="right" class="xl63"&gt;1&lt;/TD&gt;&lt;TD align="right" class="xl63"&gt;1&lt;/TD&gt;&lt;TD align="right" class="xl63"&gt;0&lt;/TD&gt;&lt;TD align="right" class="xl63"&gt;2&lt;/TD&gt;&lt;/TR&gt;&lt;TR&gt;&lt;TD height="20"&gt;0023&lt;/TD&gt;&lt;TD align="right" class="xl63"&gt;84&lt;/TD&gt;&lt;TD align="right" class="xl63"&gt;1&lt;/TD&gt;&lt;TD align="right" class="xl63"&gt;1&lt;/TD&gt;&lt;TD align="right" class="xl63"&gt;1&lt;/TD&gt;&lt;TD align="right" class="xl63"&gt;3&lt;/TD&gt;&lt;/TR&gt;&lt;TR&gt;&lt;TD height="20"&gt;0051&lt;/TD&gt;&lt;TD align="right" class="xl63"&gt;76&lt;/TD&gt;&lt;TD align="right" class="xl63"&gt;1&lt;/TD&gt;&lt;TD align="right" class="xl63"&gt;0&lt;/TD&gt;&lt;TD align="right" class="xl63"&gt;0&lt;/TD&gt;&lt;TD align="right" class="xl63"&gt;1&lt;/TD&gt;&lt;/TR&gt;&lt;TR&gt;&lt;TD height="20"&gt;0051&lt;/TD&gt;&lt;TD align="right" class="xl63"&gt;67&lt;/TD&gt;&lt;TD align="right" class="xl63"&gt;1&lt;/TD&gt;&lt;TD align="right" class="xl63"&gt;1&lt;/TD&gt;&lt;TD align="right" class="xl63"&gt;1&lt;/TD&gt;&lt;TD align="right" class="xl63"&gt;2&lt;/TD&gt;&lt;/TR&gt;&lt;TR&gt;&lt;TD height="20"&gt;0051&lt;/TD&gt;&lt;TD align="right" class="xl63"&gt;68&lt;/TD&gt;&lt;TD align="right" class="xl63"&gt;1&lt;/TD&gt;&lt;TD align="right" class="xl63"&gt;1&lt;/TD&gt;&lt;TD align="right" class="xl63"&gt;0&lt;/TD&gt;&lt;TD align="right" class="xl63"&gt;3&lt;/TD&gt;&lt;/TR&gt;&lt;/TBODY&gt;&lt;/TABLE&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;## The Code I used in PROC Logistic for conditional logistic regression;&lt;/P&gt;&lt;P&gt;PROC LOGISTIC DATA= EX ;&lt;/P&gt;&lt;P&gt;class Tx(REF='0') B1(REF='0')&amp;nbsp; /param=ref;&lt;/P&gt;&lt;P&gt;MODEL OUTCOME(EVENT='0')= Tx B1 C1 B1*Tx&amp;nbsp; / expb&amp;nbsp; ; &lt;/P&gt;&lt;P&gt;strata match_ID;&lt;/P&gt;&lt;P&gt;run;&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;&lt;SPAN style="font-size: 13.3333330154419px;"&gt;## The Code I used in PROC GENMOD for 1:2 matched data ; &lt;BR /&gt;&lt;/SPAN&gt;&lt;/P&gt;&lt;P&gt;PROc GENMOD DATA=ex;&lt;/P&gt;&lt;P&gt;CLASS MATCH_ID Tx(REF='0') B1(REF='0') /param=ref;&lt;/P&gt;&lt;P&gt;MODEL OUTCOME&amp;nbsp; =Tx B1 C1 B1*Tx&amp;nbsp; /dist=BIN link=logit&amp;nbsp; ;&lt;/P&gt;&lt;P&gt;repeated subject=MATCH_ID/type=exch;&lt;/P&gt;&lt;P&gt;run;&lt;/P&gt;&lt;P&gt;Sincerely thanks for your help ~&lt;/P&gt;&lt;/BODY&gt;&lt;/HTML&gt;</description>
    <pubDate>Sat, 22 Aug 2015 04:15:43 GMT</pubDate>
    <dc:creator>THS</dc:creator>
    <dc:date>2015-08-22T04:15:43Z</dc:date>
    <item>
      <title>Conditional logistic regression using proc logistic or Proc genmod ?</title>
      <link>https://communities.sas.com/t5/Statistical-Procedures/Conditional-logistic-regression-using-proc-logistic-or-Proc/m-p/205164#M11030</link>
      <description>&lt;HTML&gt;&lt;HEAD&gt;&lt;/HEAD&gt;&lt;BODY&gt;&lt;P&gt;Hello~ &lt;/P&gt;&lt;P&gt;I'm trying to estimate the Odds ratio of a treatment after adjusting confounding factors in a 1:2 matched data sets (ex file in the attachement)&lt;/P&gt;&lt;P&gt;Due to the dependence between these data, I'm using conditional logistic regression as statistical method.&lt;/P&gt;&lt;P&gt;PROC Logistic &amp;amp; PROC GENMOD all seems able to deal with matched data well but reported differently.&lt;BR /&gt;I'm wondering what is the difference between proc logistic&amp;nbsp; &amp;amp; proc genmod for dealing with matched data&lt;BR /&gt;and which would be better or more accurate ? .&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt; ## ex data set:&lt;/P&gt;&lt;P&gt;&lt;A href="http://https://www.dropbox.com/s/k3b4yglsofsr4u4/ex.sas7bdat?dl=0"&gt;https://www.dropbox.com/s/k3b4yglsofsr4u4/ex.sas7bdat?dl=0&lt;/A&gt;&lt;/P&gt;&lt;P&gt;Treatment option: Tx; Outcome: Outcome;&amp;nbsp; Confounding factors: B1, C1, B1*Tx;&lt;/P&gt;&lt;TABLE border="0" cellpadding="0" cellspacing="0" style="width: 417px;"&gt;&lt;TBODY&gt;&lt;TR&gt;&lt;TD height="20" width="97"&gt;MATCH_ID&lt;/TD&gt;&lt;TD width="64"&gt;C1&lt;/TD&gt;&lt;TD width="64"&gt;B1&lt;/TD&gt;&lt;TD width="64"&gt;Tx&lt;/TD&gt;&lt;TD width="64"&gt;OUTCOME&lt;/TD&gt;&lt;TD width="64"&gt;STR&lt;/TD&gt;&lt;/TR&gt;&lt;TR&gt;&lt;TD height="20"&gt;0023&lt;/TD&gt;&lt;TD align="right" class="xl63"&gt;78&lt;/TD&gt;&lt;TD align="right" class="xl63"&gt;1&lt;/TD&gt;&lt;TD align="right" class="xl63"&gt;0&lt;/TD&gt;&lt;TD align="right" class="xl63"&gt;0&lt;/TD&gt;&lt;TD align="right" class="xl63"&gt;1&lt;/TD&gt;&lt;/TR&gt;&lt;TR&gt;&lt;TD height="20"&gt;0023&lt;/TD&gt;&lt;TD align="right" class="xl63"&gt;64&lt;/TD&gt;&lt;TD align="right" class="xl63"&gt;1&lt;/TD&gt;&lt;TD align="right" class="xl63"&gt;1&lt;/TD&gt;&lt;TD align="right" class="xl63"&gt;0&lt;/TD&gt;&lt;TD align="right" class="xl63"&gt;2&lt;/TD&gt;&lt;/TR&gt;&lt;TR&gt;&lt;TD height="20"&gt;0023&lt;/TD&gt;&lt;TD align="right" class="xl63"&gt;84&lt;/TD&gt;&lt;TD align="right" class="xl63"&gt;1&lt;/TD&gt;&lt;TD align="right" class="xl63"&gt;1&lt;/TD&gt;&lt;TD align="right" class="xl63"&gt;1&lt;/TD&gt;&lt;TD align="right" class="xl63"&gt;3&lt;/TD&gt;&lt;/TR&gt;&lt;TR&gt;&lt;TD height="20"&gt;0051&lt;/TD&gt;&lt;TD align="right" class="xl63"&gt;76&lt;/TD&gt;&lt;TD align="right" class="xl63"&gt;1&lt;/TD&gt;&lt;TD align="right" class="xl63"&gt;0&lt;/TD&gt;&lt;TD align="right" class="xl63"&gt;0&lt;/TD&gt;&lt;TD align="right" class="xl63"&gt;1&lt;/TD&gt;&lt;/TR&gt;&lt;TR&gt;&lt;TD height="20"&gt;0051&lt;/TD&gt;&lt;TD align="right" class="xl63"&gt;67&lt;/TD&gt;&lt;TD align="right" class="xl63"&gt;1&lt;/TD&gt;&lt;TD align="right" class="xl63"&gt;1&lt;/TD&gt;&lt;TD align="right" class="xl63"&gt;1&lt;/TD&gt;&lt;TD align="right" class="xl63"&gt;2&lt;/TD&gt;&lt;/TR&gt;&lt;TR&gt;&lt;TD height="20"&gt;0051&lt;/TD&gt;&lt;TD align="right" class="xl63"&gt;68&lt;/TD&gt;&lt;TD align="right" class="xl63"&gt;1&lt;/TD&gt;&lt;TD align="right" class="xl63"&gt;1&lt;/TD&gt;&lt;TD align="right" class="xl63"&gt;0&lt;/TD&gt;&lt;TD align="right" class="xl63"&gt;3&lt;/TD&gt;&lt;/TR&gt;&lt;/TBODY&gt;&lt;/TABLE&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;## The Code I used in PROC Logistic for conditional logistic regression;&lt;/P&gt;&lt;P&gt;PROC LOGISTIC DATA= EX ;&lt;/P&gt;&lt;P&gt;class Tx(REF='0') B1(REF='0')&amp;nbsp; /param=ref;&lt;/P&gt;&lt;P&gt;MODEL OUTCOME(EVENT='0')= Tx B1 C1 B1*Tx&amp;nbsp; / expb&amp;nbsp; ; &lt;/P&gt;&lt;P&gt;strata match_ID;&lt;/P&gt;&lt;P&gt;run;&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;&lt;SPAN style="font-size: 13.3333330154419px;"&gt;## The Code I used in PROC GENMOD for 1:2 matched data ; &lt;BR /&gt;&lt;/SPAN&gt;&lt;/P&gt;&lt;P&gt;PROc GENMOD DATA=ex;&lt;/P&gt;&lt;P&gt;CLASS MATCH_ID Tx(REF='0') B1(REF='0') /param=ref;&lt;/P&gt;&lt;P&gt;MODEL OUTCOME&amp;nbsp; =Tx B1 C1 B1*Tx&amp;nbsp; /dist=BIN link=logit&amp;nbsp; ;&lt;/P&gt;&lt;P&gt;repeated subject=MATCH_ID/type=exch;&lt;/P&gt;&lt;P&gt;run;&lt;/P&gt;&lt;P&gt;Sincerely thanks for your help ~&lt;/P&gt;&lt;/BODY&gt;&lt;/HTML&gt;</description>
      <pubDate>Sat, 22 Aug 2015 04:15:43 GMT</pubDate>
      <guid>https://communities.sas.com/t5/Statistical-Procedures/Conditional-logistic-regression-using-proc-logistic-or-Proc/m-p/205164#M11030</guid>
      <dc:creator>THS</dc:creator>
      <dc:date>2015-08-22T04:15:43Z</dc:date>
    </item>
    <item>
      <title>Re: Conditional logistic regression using proc logistic or Proc genmod ?</title>
      <link>https://communities.sas.com/t5/Statistical-Procedures/Conditional-logistic-regression-using-proc-logistic-or-Proc/m-p/224482#M11858</link>
      <description>&lt;P&gt;The two procedures use entirely different estimation methods. &amp;nbsp;Conditional logistic regression in PROC LOGISTIC maximizes a conditional likelihood, while PROC GENMOD uses the Generalized Estimating Equations (GEE) method which is not a likelihood-based method. These methods, and others, are compared in the book "Logistic Regression Using SAS: Theory and Application, Second Edition," (Allison, P., SAS Institute, 2012).&amp;nbsp;&lt;/P&gt;</description>
      <pubDate>Tue, 08 Sep 2015 19:14:55 GMT</pubDate>
      <guid>https://communities.sas.com/t5/Statistical-Procedures/Conditional-logistic-regression-using-proc-logistic-or-Proc/m-p/224482#M11858</guid>
      <dc:creator>StatDave</dc:creator>
      <dc:date>2015-09-08T19:14:55Z</dc:date>
    </item>
  </channel>
</rss>

