<?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: Why HPGENSELECT uses chi-square to test the significance of coefficient estimates? in SAS Procedures</title>
    <link>https://communities.sas.com/t5/SAS-Procedures/Why-HPGENSELECT-uses-chi-square-to-test-the-significance-of/m-p/306859#M61062</link>
    <description>&lt;P&gt;You are correct that for OLS regression and normally distributed errors you can use t tests. However,&amp;nbsp;HPGENSELECT is most closely related to the GENMOD procedure, not the GLM procedure. For generalized linear models, the errors are not normally distributed and the solution technique is maximum likelihood estimation. The&amp;nbsp;docs for PROC LOGISTIC and PROC GENMOD mention that confidence intervals are based on the likelihood ratio, and the statstic that is used has an asymptotic chi-square distribution:&lt;/P&gt;
&lt;P&gt;LOGISTIC: &lt;A href="http://support.sas.com/documentation/cdl/en/statug/68162/HTML/default/viewer.htm#statug_logistic_details18.htm" target="_blank"&gt;http://support.sas.com/documentation/cdl/en/statug/68162/HTML/default/viewer.htm#statug_logistic_details18.htm&lt;/A&gt;&lt;/P&gt;
&lt;P&gt;GENMOD:&amp;nbsp;&lt;A href="http://support.sas.com/documentation/cdl/en/statug/68162/HTML/default/viewer.htm#statug_genmod_details17.htm" target="_blank"&gt;http://support.sas.com/documentation/cdl/en/statug/68162/HTML/default/viewer.htm#statug_genmod_details17.htm&lt;/A&gt;&lt;/P&gt;</description>
    <pubDate>Mon, 24 Oct 2016 15:57:52 GMT</pubDate>
    <dc:creator>Rick_SAS</dc:creator>
    <dc:date>2016-10-24T15:57:52Z</dc:date>
    <item>
      <title>Why HPGENSELECT uses chi-square to test the significance of coefficient estimates?</title>
      <link>https://communities.sas.com/t5/SAS-Procedures/Why-HPGENSELECT-uses-chi-square-to-test-the-significance-of/m-p/306087#M60958</link>
      <description>&lt;P&gt;Usually t-test is applied to test the significance of coefficient estimates. But HPGENSELECT uses chi-square test (see table below). Why?&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;&lt;EM&gt;Parameter Estimates from HPGENSELECT&lt;/EM&gt;&lt;/P&gt;&lt;TABLE&gt;&lt;TBODY&gt;&lt;TR&gt;&lt;TD&gt;&lt;P&gt;&lt;STRONG&gt;Parameter&lt;/STRONG&gt;&lt;/P&gt;&lt;/TD&gt;&lt;TD&gt;&lt;P&gt;&lt;STRONG&gt;DF&lt;/STRONG&gt;&lt;/P&gt;&lt;/TD&gt;&lt;TD&gt;&lt;P&gt;&lt;STRONG&gt;Estimate&lt;/STRONG&gt;&lt;/P&gt;&lt;/TD&gt;&lt;TD&gt;&lt;P&gt;&lt;STRONG&gt;Standard Error&lt;/STRONG&gt;&lt;/P&gt;&lt;/TD&gt;&lt;TD&gt;&lt;P&gt;&lt;STRONG&gt;Chi-Square&lt;/STRONG&gt;&lt;/P&gt;&lt;/TD&gt;&lt;TD&gt;&lt;P&gt;&lt;STRONG&gt;Pr&amp;nbsp;&amp;gt;&amp;nbsp;ChiSq&lt;/STRONG&gt;&lt;/P&gt;&lt;/TD&gt;&lt;/TR&gt;&lt;TR&gt;&lt;TD&gt;&lt;P&gt;&lt;STRONG&gt;Intercept&lt;/STRONG&gt;&lt;/P&gt;&lt;/TD&gt;&lt;TD&gt;&lt;P&gt;1&lt;/P&gt;&lt;/TD&gt;&lt;TD&gt;&lt;P&gt;3.405338&lt;/P&gt;&lt;/TD&gt;&lt;TD&gt;&lt;P&gt;0.142788&lt;/P&gt;&lt;/TD&gt;&lt;TD&gt;&lt;P&gt;568.768&lt;/P&gt;&lt;/TD&gt;&lt;TD&gt;&lt;P&gt;&amp;lt;.0001&lt;/P&gt;&lt;/TD&gt;&lt;/TR&gt;&lt;/TBODY&gt;&lt;/TABLE&gt;</description>
      <pubDate>Thu, 20 Oct 2016 20:45:13 GMT</pubDate>
      <guid>https://communities.sas.com/t5/SAS-Procedures/Why-HPGENSELECT-uses-chi-square-to-test-the-significance-of/m-p/306087#M60958</guid>
      <dc:creator>Junwang09</dc:creator>
      <dc:date>2016-10-20T20:45:13Z</dc:date>
    </item>
    <item>
      <title>Re: Why HPGENSELECT uses chi-square to test the significance of coefficient estimates?</title>
      <link>https://communities.sas.com/t5/SAS-Procedures/Why-HPGENSELECT-uses-chi-square-to-test-the-significance-of/m-p/306093#M60962</link>
      <description>&lt;P&gt;You can change that, can't you?&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;P&gt;&lt;A href="http://support.sas.com/documentation/cdl/en/stathpug/66410/HTML/default/viewer.htm#stathpug_hpgenselect_syntax11.htm" target="_blank"&gt;http://support.sas.com/documentation/cdl/en/stathpug/66410/HTML/default/viewer.htm#stathpug_hpgenselect_syntax11.htm&lt;/A&gt;&lt;/P&gt;</description>
      <pubDate>Thu, 20 Oct 2016 20:52:28 GMT</pubDate>
      <guid>https://communities.sas.com/t5/SAS-Procedures/Why-HPGENSELECT-uses-chi-square-to-test-the-significance-of/m-p/306093#M60962</guid>
      <dc:creator>Reeza</dc:creator>
      <dc:date>2016-10-20T20:52:28Z</dc:date>
    </item>
    <item>
      <title>Re: Why HPGENSELECT uses chi-square to test the significance of coefficient estimates?</title>
      <link>https://communities.sas.com/t5/SAS-Procedures/Why-HPGENSELECT-uses-chi-square-to-test-the-significance-of/m-p/306284#M60987</link>
      <description>&lt;P&gt;Reeza, thanks a lot for your help. I try to understand that how Chi-square can be used to test the significance of coefficient. Do you have any reference? thanks!&lt;/P&gt;</description>
      <pubDate>Fri, 21 Oct 2016 13:53:03 GMT</pubDate>
      <guid>https://communities.sas.com/t5/SAS-Procedures/Why-HPGENSELECT-uses-chi-square-to-test-the-significance-of/m-p/306284#M60987</guid>
      <dc:creator>Junwang09</dc:creator>
      <dc:date>2016-10-21T13:53:03Z</dc:date>
    </item>
    <item>
      <title>Re: Why HPGENSELECT uses chi-square to test the significance of coefficient estimates?</title>
      <link>https://communities.sas.com/t5/SAS-Procedures/Why-HPGENSELECT-uses-chi-square-to-test-the-significance-of/m-p/306859#M61062</link>
      <description>&lt;P&gt;You are correct that for OLS regression and normally distributed errors you can use t tests. However,&amp;nbsp;HPGENSELECT is most closely related to the GENMOD procedure, not the GLM procedure. For generalized linear models, the errors are not normally distributed and the solution technique is maximum likelihood estimation. The&amp;nbsp;docs for PROC LOGISTIC and PROC GENMOD mention that confidence intervals are based on the likelihood ratio, and the statstic that is used has an asymptotic chi-square distribution:&lt;/P&gt;
&lt;P&gt;LOGISTIC: &lt;A href="http://support.sas.com/documentation/cdl/en/statug/68162/HTML/default/viewer.htm#statug_logistic_details18.htm" target="_blank"&gt;http://support.sas.com/documentation/cdl/en/statug/68162/HTML/default/viewer.htm#statug_logistic_details18.htm&lt;/A&gt;&lt;/P&gt;
&lt;P&gt;GENMOD:&amp;nbsp;&lt;A href="http://support.sas.com/documentation/cdl/en/statug/68162/HTML/default/viewer.htm#statug_genmod_details17.htm" target="_blank"&gt;http://support.sas.com/documentation/cdl/en/statug/68162/HTML/default/viewer.htm#statug_genmod_details17.htm&lt;/A&gt;&lt;/P&gt;</description>
      <pubDate>Mon, 24 Oct 2016 15:57:52 GMT</pubDate>
      <guid>https://communities.sas.com/t5/SAS-Procedures/Why-HPGENSELECT-uses-chi-square-to-test-the-significance-of/m-p/306859#M61062</guid>
      <dc:creator>Rick_SAS</dc:creator>
      <dc:date>2016-10-24T15:57:52Z</dc:date>
    </item>
    <item>
      <title>Re: Why HPGENSELECT uses chi-square to test the significance of coefficient estimates?</title>
      <link>https://communities.sas.com/t5/SAS-Procedures/Why-HPGENSELECT-uses-chi-square-to-test-the-significance-of/m-p/306901#M61066</link>
      <description>&lt;P&gt;Thanks for your reply. The links you attached is very helpful.&lt;/P&gt;</description>
      <pubDate>Mon, 24 Oct 2016 18:25:17 GMT</pubDate>
      <guid>https://communities.sas.com/t5/SAS-Procedures/Why-HPGENSELECT-uses-chi-square-to-test-the-significance-of/m-p/306901#M61066</guid>
      <dc:creator>Junwang09</dc:creator>
      <dc:date>2016-10-24T18:25:17Z</dc:date>
    </item>
  </channel>
</rss>

