<?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: Number of components in mixture model in Statistical Procedures</title>
    <link>https://communities.sas.com/t5/Statistical-Procedures/Number-of-components-in-mixture-model/m-p/700254#M33772</link>
    <description>Hello,&lt;BR /&gt;If you fit multiple models within one PROC FMM call by using the KMIN= and KMAX= options, the procedure will use the BIC (smaller values are better) to choose the model with the best fit. You can use the CRITERION= option to the PROC FMM statement to specify a different model selection criterion (AIC, AICC, etc). If you fit several models in different PROC FMM invocations, you can compare the criterion values in the separate "Fit Statistics" tables to choose a best model.</description>
    <pubDate>Thu, 19 Nov 2020 16:29:54 GMT</pubDate>
    <dc:creator>DaveKsas</dc:creator>
    <dc:date>2020-11-19T16:29:54Z</dc:date>
    <item>
      <title>Number of components in mixture model</title>
      <link>https://communities.sas.com/t5/Statistical-Procedures/Number-of-components-in-mixture-model/m-p/700195#M33771</link>
      <description>&lt;P&gt;How to know which components number is the best model in proc FMM? Any code as references?&lt;/P&gt;</description>
      <pubDate>Thu, 19 Nov 2020 13:29:07 GMT</pubDate>
      <guid>https://communities.sas.com/t5/Statistical-Procedures/Number-of-components-in-mixture-model/m-p/700195#M33771</guid>
      <dc:creator>Jess03ng</dc:creator>
      <dc:date>2020-11-19T13:29:07Z</dc:date>
    </item>
    <item>
      <title>Re: Number of components in mixture model</title>
      <link>https://communities.sas.com/t5/Statistical-Procedures/Number-of-components-in-mixture-model/m-p/700254#M33772</link>
      <description>Hello,&lt;BR /&gt;If you fit multiple models within one PROC FMM call by using the KMIN= and KMAX= options, the procedure will use the BIC (smaller values are better) to choose the model with the best fit. You can use the CRITERION= option to the PROC FMM statement to specify a different model selection criterion (AIC, AICC, etc). If you fit several models in different PROC FMM invocations, you can compare the criterion values in the separate "Fit Statistics" tables to choose a best model.</description>
      <pubDate>Thu, 19 Nov 2020 16:29:54 GMT</pubDate>
      <guid>https://communities.sas.com/t5/Statistical-Procedures/Number-of-components-in-mixture-model/m-p/700254#M33772</guid>
      <dc:creator>DaveKsas</dc:creator>
      <dc:date>2020-11-19T16:29:54Z</dc:date>
    </item>
  </channel>
</rss>

