<?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 Missing data in PHREG with repeated covariate measures in New SAS User</title>
    <link>https://communities.sas.com/t5/New-SAS-User/Missing-data-in-PHREG-with-repeated-covariate-measures/m-p/503437#M824</link>
    <description>&lt;P&gt;Hello!&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;I am running PHREG with repeated covariate measures and I cannot understand how SAS deals with missing data. I specifically created a data set&amp;nbsp;with full repeated covariate data (i.e.&amp;nbsp;there are no missing values in any of the variables). Nevertheless, I still get notes in the LOG such as "5 event observations have missing values in the time-dependent covariates. They are not counted as event observations, but they may still be used in the risk sets of other event times."&amp;nbsp;Of course the outcome and follow-up time are also complete. Does anyone knows why this may be happening? The code I use is:&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;&lt;FONT color="#000080" face="Courier New" size="3"&gt;&lt;STRONG&gt;proc&lt;/STRONG&gt;&lt;/FONT&gt; &lt;STRONG&gt;&lt;FONT color="#000080" face="Courier New" size="3"&gt;phreg&lt;/FONT&gt;&lt;/STRONG&gt; &lt;FONT color="#0000ff" face="Courier New" size="3"&gt;data&lt;/FONT&gt;&lt;FONT face="Courier New" size="3"&gt;=check;&lt;/FONT&gt;&lt;/P&gt;&lt;P&gt;&lt;FONT color="#0000ff" face="Courier New" size="3"&gt;&amp;nbsp;&amp;nbsp; where&lt;/FONT&gt;&lt;FONT face="Courier New" size="3"&gt; cohort&amp;gt;&lt;/FONT&gt;&lt;STRONG&gt;&lt;FONT color="#008080" face="Courier New" size="3"&gt;1&lt;/FONT&gt;&lt;/STRONG&gt;&lt;FONT face="Courier New" size="3"&gt; and &lt;FONT face="Courier New"&gt;Years&lt;/FONT&gt;~=&lt;/FONT&gt;&lt;STRONG&gt;&lt;FONT color="#008080" face="Courier New" size="3"&gt;.&lt;/FONT&gt;&lt;/STRONG&gt;&lt;FONT face="Courier New" size="3"&gt;;&lt;/FONT&gt;&lt;/P&gt;&lt;P&gt;&lt;FONT color="#0000ff" face="Courier New" size="3"&gt;&amp;nbsp;&amp;nbsp; class&lt;/FONT&gt;&lt;FONT face="Courier New" size="3"&gt; sex(&lt;/FONT&gt;&lt;FONT color="#0000ff" face="Courier New" size="3"&gt;ref&lt;/FONT&gt;&lt;FONT face="Courier New" size="3"&gt;=&lt;/FONT&gt;&lt;FONT color="#800080" face="Courier New" size="3"&gt;"1"&lt;/FONT&gt;&lt;FONT face="Courier New" size="3"&gt;) cohort(&lt;/FONT&gt;&lt;FONT color="#0000ff" face="Courier New" size="3"&gt;ref&lt;/FONT&gt;&lt;FONT face="Courier New" size="3"&gt;=&lt;/FONT&gt;&lt;FONT color="#800080" face="Courier New" size="3"&gt;"2"&lt;/FONT&gt;&lt;FONT face="Courier New" size="3"&gt;);&lt;/FONT&gt;&lt;/P&gt;&lt;P&gt;&lt;FONT color="#0000ff" face="Courier New" size="3"&gt;&amp;nbsp;&amp;nbsp; model&lt;/FONT&gt;&lt;FONT face="Courier New" size="3"&gt; &lt;FONT face="Courier New"&gt;Years&lt;/FONT&gt;*Outcome(&lt;/FONT&gt;&lt;STRONG&gt;&lt;FONT color="#008080" face="Courier New" size="3"&gt;0&lt;/FONT&gt;&lt;/STRONG&gt;&lt;FONT face="Courier New" size="3"&gt;)=cohort sex bodymassindex &lt;/FONT&gt;&lt;FONT face="Courier New" size="3"&gt;/ &lt;/FONT&gt;&lt;FONT color="#0000ff" face="Courier New" size="3"&gt;ties&lt;/FONT&gt;&lt;FONT face="Courier New" size="3"&gt;=breslow &lt;/FONT&gt;&lt;FONT color="#0000ff" face="Courier New" size="3"&gt;risklimits&lt;/FONT&gt; &lt;FONT color="#0000ff" face="Courier New" size="3"&gt;selection&lt;/FONT&gt;&lt;FONT face="Courier New" size="3"&gt;=backward &lt;/FONT&gt;&lt;FONT color="#0000ff" face="Courier New" size="3"&gt;slstay&lt;/FONT&gt;&lt;FONT face="Courier New" size="3"&gt;=&lt;/FONT&gt;&lt;STRONG&gt;&lt;FONT color="#008080" face="Courier New" size="3"&gt;0.08&lt;/FONT&gt;&lt;/STRONG&gt; &lt;FONT color="#0000ff" face="Courier New" size="3"&gt;include&lt;/FONT&gt;&lt;FONT face="Courier New" size="3"&gt;=&lt;/FONT&gt;&lt;STRONG&gt;&lt;FONT color="#008080" face="Courier New" size="3"&gt;1&lt;/FONT&gt;&lt;/STRONG&gt;&lt;FONT face="Courier New" size="3"&gt;;&lt;/FONT&gt;&lt;/P&gt;&lt;P&gt;&lt;FONT color="#0000ff" face="Courier New" size="3"&gt;&amp;nbsp;&amp;nbsp; array&lt;/FONT&gt;&lt;FONT face="Courier New" size="3"&gt; adur{*} dur1-dur6 dur8 dur10 dur14;&lt;/FONT&gt;&lt;/P&gt;&lt;P&gt;&lt;FONT color="#0000ff" face="Courier New" size="3"&gt;&amp;nbsp;&amp;nbsp; array&lt;/FONT&gt;&lt;FONT face="Courier New" size="3"&gt; abmi{*} mbmi1-mbmi6 mbmi8 mbmi10 mbmi14;&lt;/FONT&gt;&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;&lt;FONT color="#0000ff" face="Courier New" size="3"&gt;&amp;nbsp;&amp;nbsp; do&lt;/FONT&gt;&lt;FONT face="Courier New" size="3"&gt; i=&lt;/FONT&gt;&lt;STRONG&gt;&lt;FONT color="#008080" face="Courier New" size="3"&gt;1&lt;/FONT&gt;&lt;/STRONG&gt; &lt;FONT color="#0000ff" face="Courier New" size="3"&gt;to&lt;/FONT&gt; &lt;STRONG&gt;&lt;FONT color="#008080" face="Courier New" size="3"&gt;9&lt;/FONT&gt;&lt;/STRONG&gt;&lt;FONT face="Courier New" size="3"&gt;;&lt;/FONT&gt;&lt;/P&gt;&lt;P&gt;&lt;FONT color="#0000ff" face="Courier New" size="3"&gt;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp; if&lt;/FONT&gt;&lt;FONT face="Courier New" size="3"&gt; (&lt;FONT face="Courier New"&gt;Years&lt;/FONT&gt; ge adur{i}) and (adur{i}~=&lt;/FONT&gt;&lt;STRONG&gt;&lt;FONT color="#008080" face="Courier New" size="3"&gt;.&lt;/FONT&gt;&lt;/STRONG&gt;&lt;FONT face="Courier New" size="3"&gt;) &lt;/FONT&gt;&lt;FONT color="#0000ff" face="Courier New" size="3"&gt;then&lt;/FONT&gt; &lt;FONT color="#0000ff" face="Courier New" size="3"&gt;do&lt;/FONT&gt;&lt;FONT face="Courier New" size="3"&gt;;&lt;/FONT&gt;&lt;/P&gt;&lt;P&gt;&lt;FONT face="Courier New" size="3"&gt;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp; bodymassindex=abmi{i};&lt;/FONT&gt;&lt;/P&gt;&lt;P&gt;&lt;FONT color="#0000ff" face="Courier New" size="3"&gt;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp; end&lt;/FONT&gt;&lt;FONT face="Courier New" size="3"&gt;;&lt;/FONT&gt;&lt;/P&gt;&lt;P&gt;&lt;FONT color="#0000ff" face="Courier New" size="3"&gt;&amp;nbsp;&amp;nbsp; end&lt;/FONT&gt;&lt;FONT face="Courier New" size="3"&gt;;&lt;/FONT&gt;&lt;/P&gt;&lt;P&gt;&lt;FONT color="#000080" face="Courier New" size="3"&gt;&lt;STRONG&gt;run&lt;/STRONG&gt;&lt;/FONT&gt;&lt;FONT face="Courier New" size="3"&gt;;&lt;/FONT&gt;&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;Thank you!&lt;BR /&gt;Tina.&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;P.S. The reason I am concerned about this is that when I use the same exact data set&amp;nbsp;with PROC LIFETEST, I get very different results. When&amp;nbsp;covariates outside the fixed cohort and sex are not included in PHREG the effect of cohort is not significant, just like in LIFETEST. However, when bmi is included as a covariate with repeated measures, the effect of cohort becomes very significant, though bmi increases over time across all cohorts (though it is lower at study entry in one compared to the other two cohorts, bmi becomes similar across cohorts by year 3). I was thus wondering whether the 5 events not counted as such may be the answer, although I am not sure which 5 are excluded as cases - all have data on bmi throughout follow-up.&lt;/P&gt;</description>
    <pubDate>Thu, 11 Oct 2018 16:55:13 GMT</pubDate>
    <dc:creator>SAS_help_needed</dc:creator>
    <dc:date>2018-10-11T16:55:13Z</dc:date>
    <item>
      <title>Missing data in PHREG with repeated covariate measures</title>
      <link>https://communities.sas.com/t5/New-SAS-User/Missing-data-in-PHREG-with-repeated-covariate-measures/m-p/503437#M824</link>
      <description>&lt;P&gt;Hello!&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;I am running PHREG with repeated covariate measures and I cannot understand how SAS deals with missing data. I specifically created a data set&amp;nbsp;with full repeated covariate data (i.e.&amp;nbsp;there are no missing values in any of the variables). Nevertheless, I still get notes in the LOG such as "5 event observations have missing values in the time-dependent covariates. They are not counted as event observations, but they may still be used in the risk sets of other event times."&amp;nbsp;Of course the outcome and follow-up time are also complete. Does anyone knows why this may be happening? The code I use is:&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;&lt;FONT color="#000080" face="Courier New" size="3"&gt;&lt;STRONG&gt;proc&lt;/STRONG&gt;&lt;/FONT&gt; &lt;STRONG&gt;&lt;FONT color="#000080" face="Courier New" size="3"&gt;phreg&lt;/FONT&gt;&lt;/STRONG&gt; &lt;FONT color="#0000ff" face="Courier New" size="3"&gt;data&lt;/FONT&gt;&lt;FONT face="Courier New" size="3"&gt;=check;&lt;/FONT&gt;&lt;/P&gt;&lt;P&gt;&lt;FONT color="#0000ff" face="Courier New" size="3"&gt;&amp;nbsp;&amp;nbsp; where&lt;/FONT&gt;&lt;FONT face="Courier New" size="3"&gt; cohort&amp;gt;&lt;/FONT&gt;&lt;STRONG&gt;&lt;FONT color="#008080" face="Courier New" size="3"&gt;1&lt;/FONT&gt;&lt;/STRONG&gt;&lt;FONT face="Courier New" size="3"&gt; and &lt;FONT face="Courier New"&gt;Years&lt;/FONT&gt;~=&lt;/FONT&gt;&lt;STRONG&gt;&lt;FONT color="#008080" face="Courier New" size="3"&gt;.&lt;/FONT&gt;&lt;/STRONG&gt;&lt;FONT face="Courier New" size="3"&gt;;&lt;/FONT&gt;&lt;/P&gt;&lt;P&gt;&lt;FONT color="#0000ff" face="Courier New" size="3"&gt;&amp;nbsp;&amp;nbsp; class&lt;/FONT&gt;&lt;FONT face="Courier New" size="3"&gt; sex(&lt;/FONT&gt;&lt;FONT color="#0000ff" face="Courier New" size="3"&gt;ref&lt;/FONT&gt;&lt;FONT face="Courier New" size="3"&gt;=&lt;/FONT&gt;&lt;FONT color="#800080" face="Courier New" size="3"&gt;"1"&lt;/FONT&gt;&lt;FONT face="Courier New" size="3"&gt;) cohort(&lt;/FONT&gt;&lt;FONT color="#0000ff" face="Courier New" size="3"&gt;ref&lt;/FONT&gt;&lt;FONT face="Courier New" size="3"&gt;=&lt;/FONT&gt;&lt;FONT color="#800080" face="Courier New" size="3"&gt;"2"&lt;/FONT&gt;&lt;FONT face="Courier New" size="3"&gt;);&lt;/FONT&gt;&lt;/P&gt;&lt;P&gt;&lt;FONT color="#0000ff" face="Courier New" size="3"&gt;&amp;nbsp;&amp;nbsp; model&lt;/FONT&gt;&lt;FONT face="Courier New" size="3"&gt; &lt;FONT face="Courier New"&gt;Years&lt;/FONT&gt;*Outcome(&lt;/FONT&gt;&lt;STRONG&gt;&lt;FONT color="#008080" face="Courier New" size="3"&gt;0&lt;/FONT&gt;&lt;/STRONG&gt;&lt;FONT face="Courier New" size="3"&gt;)=cohort sex bodymassindex &lt;/FONT&gt;&lt;FONT face="Courier New" size="3"&gt;/ &lt;/FONT&gt;&lt;FONT color="#0000ff" face="Courier New" size="3"&gt;ties&lt;/FONT&gt;&lt;FONT face="Courier New" size="3"&gt;=breslow &lt;/FONT&gt;&lt;FONT color="#0000ff" face="Courier New" size="3"&gt;risklimits&lt;/FONT&gt; &lt;FONT color="#0000ff" face="Courier New" size="3"&gt;selection&lt;/FONT&gt;&lt;FONT face="Courier New" size="3"&gt;=backward &lt;/FONT&gt;&lt;FONT color="#0000ff" face="Courier New" size="3"&gt;slstay&lt;/FONT&gt;&lt;FONT face="Courier New" size="3"&gt;=&lt;/FONT&gt;&lt;STRONG&gt;&lt;FONT color="#008080" face="Courier New" size="3"&gt;0.08&lt;/FONT&gt;&lt;/STRONG&gt; &lt;FONT color="#0000ff" face="Courier New" size="3"&gt;include&lt;/FONT&gt;&lt;FONT face="Courier New" size="3"&gt;=&lt;/FONT&gt;&lt;STRONG&gt;&lt;FONT color="#008080" face="Courier New" size="3"&gt;1&lt;/FONT&gt;&lt;/STRONG&gt;&lt;FONT face="Courier New" size="3"&gt;;&lt;/FONT&gt;&lt;/P&gt;&lt;P&gt;&lt;FONT color="#0000ff" face="Courier New" size="3"&gt;&amp;nbsp;&amp;nbsp; array&lt;/FONT&gt;&lt;FONT face="Courier New" size="3"&gt; adur{*} dur1-dur6 dur8 dur10 dur14;&lt;/FONT&gt;&lt;/P&gt;&lt;P&gt;&lt;FONT color="#0000ff" face="Courier New" size="3"&gt;&amp;nbsp;&amp;nbsp; array&lt;/FONT&gt;&lt;FONT face="Courier New" size="3"&gt; abmi{*} mbmi1-mbmi6 mbmi8 mbmi10 mbmi14;&lt;/FONT&gt;&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;&lt;FONT color="#0000ff" face="Courier New" size="3"&gt;&amp;nbsp;&amp;nbsp; do&lt;/FONT&gt;&lt;FONT face="Courier New" size="3"&gt; i=&lt;/FONT&gt;&lt;STRONG&gt;&lt;FONT color="#008080" face="Courier New" size="3"&gt;1&lt;/FONT&gt;&lt;/STRONG&gt; &lt;FONT color="#0000ff" face="Courier New" size="3"&gt;to&lt;/FONT&gt; &lt;STRONG&gt;&lt;FONT color="#008080" face="Courier New" size="3"&gt;9&lt;/FONT&gt;&lt;/STRONG&gt;&lt;FONT face="Courier New" size="3"&gt;;&lt;/FONT&gt;&lt;/P&gt;&lt;P&gt;&lt;FONT color="#0000ff" face="Courier New" size="3"&gt;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp; if&lt;/FONT&gt;&lt;FONT face="Courier New" size="3"&gt; (&lt;FONT face="Courier New"&gt;Years&lt;/FONT&gt; ge adur{i}) and (adur{i}~=&lt;/FONT&gt;&lt;STRONG&gt;&lt;FONT color="#008080" face="Courier New" size="3"&gt;.&lt;/FONT&gt;&lt;/STRONG&gt;&lt;FONT face="Courier New" size="3"&gt;) &lt;/FONT&gt;&lt;FONT color="#0000ff" face="Courier New" size="3"&gt;then&lt;/FONT&gt; &lt;FONT color="#0000ff" face="Courier New" size="3"&gt;do&lt;/FONT&gt;&lt;FONT face="Courier New" size="3"&gt;;&lt;/FONT&gt;&lt;/P&gt;&lt;P&gt;&lt;FONT face="Courier New" size="3"&gt;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp; bodymassindex=abmi{i};&lt;/FONT&gt;&lt;/P&gt;&lt;P&gt;&lt;FONT color="#0000ff" face="Courier New" size="3"&gt;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp; end&lt;/FONT&gt;&lt;FONT face="Courier New" size="3"&gt;;&lt;/FONT&gt;&lt;/P&gt;&lt;P&gt;&lt;FONT color="#0000ff" face="Courier New" size="3"&gt;&amp;nbsp;&amp;nbsp; end&lt;/FONT&gt;&lt;FONT face="Courier New" size="3"&gt;;&lt;/FONT&gt;&lt;/P&gt;&lt;P&gt;&lt;FONT color="#000080" face="Courier New" size="3"&gt;&lt;STRONG&gt;run&lt;/STRONG&gt;&lt;/FONT&gt;&lt;FONT face="Courier New" size="3"&gt;;&lt;/FONT&gt;&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;Thank you!&lt;BR /&gt;Tina.&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;P.S. The reason I am concerned about this is that when I use the same exact data set&amp;nbsp;with PROC LIFETEST, I get very different results. When&amp;nbsp;covariates outside the fixed cohort and sex are not included in PHREG the effect of cohort is not significant, just like in LIFETEST. However, when bmi is included as a covariate with repeated measures, the effect of cohort becomes very significant, though bmi increases over time across all cohorts (though it is lower at study entry in one compared to the other two cohorts, bmi becomes similar across cohorts by year 3). I was thus wondering whether the 5 events not counted as such may be the answer, although I am not sure which 5 are excluded as cases - all have data on bmi throughout follow-up.&lt;/P&gt;</description>
      <pubDate>Thu, 11 Oct 2018 16:55:13 GMT</pubDate>
      <guid>https://communities.sas.com/t5/New-SAS-User/Missing-data-in-PHREG-with-repeated-covariate-measures/m-p/503437#M824</guid>
      <dc:creator>SAS_help_needed</dc:creator>
      <dc:date>2018-10-11T16:55:13Z</dc:date>
    </item>
    <item>
      <title>Re: Missing data in PHREG with repeated covariate measures</title>
      <link>https://communities.sas.com/t5/New-SAS-User/Missing-data-in-PHREG-with-repeated-covariate-measures/m-p/503900#M881</link>
      <description>&lt;P&gt;Hi&amp;nbsp;&lt;a href="https://communities.sas.com/t5/user/viewprofilepage/user-id/172826"&gt;@SAS_help_needed&lt;/a&gt;, I did some internal checking here at SAS. Since solving this issue will require some diagnostic effort, the fastest route to an answer would be for you to contact Technical Support. Any of the methods at this link will work:&amp;nbsp;&lt;A href="https://support.sas.com/techsup/contact/" target="_blank"&gt;https://support.sas.com/techsup/contact/&lt;/A&gt;&amp;nbsp;If the resolution is something you can share, post back here so users with future similar questions will benefit. All the best to you...&lt;/P&gt;</description>
      <pubDate>Fri, 12 Oct 2018 20:52:34 GMT</pubDate>
      <guid>https://communities.sas.com/t5/New-SAS-User/Missing-data-in-PHREG-with-repeated-covariate-measures/m-p/503900#M881</guid>
      <dc:creator>BeverlyBrown</dc:creator>
      <dc:date>2018-10-12T20:52:34Z</dc:date>
    </item>
  </channel>
</rss>

