<?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: GLIMMIX How to back transform EBLUP in the original scale in Statistical Procedures</title>
    <link>https://communities.sas.com/t5/Statistical-Procedures/GLIMMIX-How-to-back-transform-EBLUP-in-the-original-scale/m-p/150607#M7929</link>
    <description>&lt;HTML&gt;&lt;HEAD&gt;&lt;/HEAD&gt;&lt;BODY&gt;&lt;P&gt;Dear Steve,&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;First of all, Yes, "male" is an numeric id and it was sorted by this variable. &lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;Second, thanks you for the tips about the "ilink" option, but as mentioned before i just need the&amp;nbsp; formula... My problem was more about mathematic rather than programming in SAS my wish. It was to back transform EBLUP in a proc IML program. I found an elegant solution, I use a logit link which is fairy similar to probit link but the reverse formula is much easier to calculate.&lt;/P&gt;&lt;P&gt;Cheers,&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;jb&lt;/P&gt;&lt;/BODY&gt;&lt;/HTML&gt;</description>
    <pubDate>Mon, 27 Jan 2014 10:41:36 GMT</pubDate>
    <dc:creator>Eisa</dc:creator>
    <dc:date>2014-01-27T10:41:36Z</dc:date>
    <item>
      <title>GLIMMIX How to back transform EBLUP in the original scale</title>
      <link>https://communities.sas.com/t5/Statistical-Procedures/GLIMMIX-How-to-back-transform-EBLUP-in-the-original-scale/m-p/150605#M7927</link>
      <description>&lt;HTML&gt;&lt;HEAD&gt;&lt;/HEAD&gt;&lt;BODY&gt;&lt;P&gt;Dear SASusers,&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;I spent several hours to search in the manual and on the web the formula to back transform the eBLUP from the proc GLIMMIX, see the code below.&lt;/P&gt;&lt;P&gt;Any ideas are welcome.&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;proc glimmix data=pocheNG asycov&amp;nbsp; ; &lt;/P&gt;&lt;P&gt;class site; &lt;/P&gt;&lt;P&gt;model surv(event ='1') =&amp;nbsp; site /s dist = binary link = probit noint ;&lt;/P&gt;&lt;P&gt;random intercept /s subject = male ;&lt;/P&gt;&lt;P&gt;random _residual_ ; *to fit an overdispersion ;&lt;/P&gt;&lt;P&gt;/**output out = a1 /ALLSTAT&amp;nbsp; ; **/&lt;/P&gt;&lt;P&gt;&lt;STRONG&gt;ods output solutionR = BLUP ;&lt;/STRONG&gt;&lt;/P&gt;&lt;P&gt;run ;&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;I know that i could have the eBLUP in the original scale from the "output statment"... but i will need this formula later.&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;QUESTION 1 : How could i back transform the eBLUP estimation in the probit scale to the original scale ?&lt;/P&gt;&lt;P&gt;Thanks you,&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;Jb&lt;/P&gt;&lt;/BODY&gt;&lt;/HTML&gt;</description>
      <pubDate>Thu, 23 Jan 2014 17:50:53 GMT</pubDate>
      <guid>https://communities.sas.com/t5/Statistical-Procedures/GLIMMIX-How-to-back-transform-EBLUP-in-the-original-scale/m-p/150605#M7927</guid>
      <dc:creator>Eisa</dc:creator>
      <dc:date>2014-01-23T17:50:53Z</dc:date>
    </item>
    <item>
      <title>Re: GLIMMIX How to back transform EBLUP in the original scale</title>
      <link>https://communities.sas.com/t5/Statistical-Procedures/GLIMMIX-How-to-back-transform-EBLUP-in-the-original-scale/m-p/150606#M7928</link>
      <description>&lt;HTML&gt;&lt;HEAD&gt;&lt;/HEAD&gt;&lt;BODY&gt;&lt;P&gt;Look up the ILINK option to the OUTPUT statement.&amp;nbsp; Something like:&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;output out=a1 pred(blup ilink)=predicted;&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;This should give an eblup for every observation in the dataset.&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;However, I want to ask if your dataset is sorted by "male".&amp;nbsp; I assume that it is a numeric id.&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;Steve Denham&lt;/P&gt;&lt;/BODY&gt;&lt;/HTML&gt;</description>
      <pubDate>Fri, 24 Jan 2014 17:51:44 GMT</pubDate>
      <guid>https://communities.sas.com/t5/Statistical-Procedures/GLIMMIX-How-to-back-transform-EBLUP-in-the-original-scale/m-p/150606#M7928</guid>
      <dc:creator>SteveDenham</dc:creator>
      <dc:date>2014-01-24T17:51:44Z</dc:date>
    </item>
    <item>
      <title>Re: GLIMMIX How to back transform EBLUP in the original scale</title>
      <link>https://communities.sas.com/t5/Statistical-Procedures/GLIMMIX-How-to-back-transform-EBLUP-in-the-original-scale/m-p/150607#M7929</link>
      <description>&lt;HTML&gt;&lt;HEAD&gt;&lt;/HEAD&gt;&lt;BODY&gt;&lt;P&gt;Dear Steve,&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;First of all, Yes, "male" is an numeric id and it was sorted by this variable. &lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;Second, thanks you for the tips about the "ilink" option, but as mentioned before i just need the&amp;nbsp; formula... My problem was more about mathematic rather than programming in SAS my wish. It was to back transform EBLUP in a proc IML program. I found an elegant solution, I use a logit link which is fairy similar to probit link but the reverse formula is much easier to calculate.&lt;/P&gt;&lt;P&gt;Cheers,&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;jb&lt;/P&gt;&lt;/BODY&gt;&lt;/HTML&gt;</description>
      <pubDate>Mon, 27 Jan 2014 10:41:36 GMT</pubDate>
      <guid>https://communities.sas.com/t5/Statistical-Procedures/GLIMMIX-How-to-back-transform-EBLUP-in-the-original-scale/m-p/150607#M7929</guid>
      <dc:creator>Eisa</dc:creator>
      <dc:date>2014-01-27T10:41:36Z</dc:date>
    </item>
    <item>
      <title>Re: GLIMMIX How to back transform EBLUP in the original scale</title>
      <link>https://communities.sas.com/t5/Statistical-Procedures/GLIMMIX-How-to-back-transform-EBLUP-in-the-original-scale/m-p/150608#M7930</link>
      <description>&lt;HTML&gt;&lt;HEAD&gt;&lt;/HEAD&gt;&lt;BODY&gt;&lt;P&gt;To get from the probit scale to the probability scale, you could use the CDF function.&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;eblup_prob_scale=CDF('NORMAL', eblup_probit_value);&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;Steve Denham&lt;/P&gt;&lt;/BODY&gt;&lt;/HTML&gt;</description>
      <pubDate>Mon, 27 Jan 2014 14:48:10 GMT</pubDate>
      <guid>https://communities.sas.com/t5/Statistical-Procedures/GLIMMIX-How-to-back-transform-EBLUP-in-the-original-scale/m-p/150608#M7930</guid>
      <dc:creator>SteveDenham</dc:creator>
      <dc:date>2014-01-27T14:48:10Z</dc:date>
    </item>
    <item>
      <title>Re: GLIMMIX How to back transform EBLUP in the original scale</title>
      <link>https://communities.sas.com/t5/Statistical-Procedures/GLIMMIX-How-to-back-transform-EBLUP-in-the-original-scale/m-p/150609#M7931</link>
      <description>&lt;HTML&gt;&lt;HEAD&gt;&lt;/HEAD&gt;&lt;BODY&gt;&lt;P&gt;Thanks Steve. &lt;/P&gt;&lt;/BODY&gt;&lt;/HTML&gt;</description>
      <pubDate>Mon, 27 Jan 2014 17:08:33 GMT</pubDate>
      <guid>https://communities.sas.com/t5/Statistical-Procedures/GLIMMIX-How-to-back-transform-EBLUP-in-the-original-scale/m-p/150609#M7931</guid>
      <dc:creator>Eisa</dc:creator>
      <dc:date>2014-01-27T17:08:33Z</dc:date>
    </item>
  </channel>
</rss>

