<?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 PS Fine Stratification in SAS in Statistical Procedures</title>
    <link>https://communities.sas.com/t5/Statistical-Procedures/PS-Fine-Stratification-in-SAS/m-p/984119#M49300</link>
    <description>&lt;P&gt;Hello, everyone&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;P&gt;Today I read a paper which used the&amp;nbsp;PS Fine Stratification as their statistical analysis method. It was inspiring as the IPTW method can inflate the pseudo-cohort by outliers (by extreme low/high propensity scores). I know the robust variance estimator can handle the correlation between clone observations but the inflation itself can affect the accuracy of the confidence intervals.&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;P&gt;By the method of&amp;nbsp;PS Fine Stratification, the IPTW-based inflation is not a problem as it will not use a pseudo-cohort. Therefore, I wonder if we can do&amp;nbsp;PS Fine Stratification in SAS by existing syntaxes. Thank you.&lt;/P&gt;</description>
    <pubDate>Thu, 26 Feb 2026 08:20:22 GMT</pubDate>
    <dc:creator>TomHsiung</dc:creator>
    <dc:date>2026-02-26T08:20:22Z</dc:date>
    <item>
      <title>PS Fine Stratification in SAS</title>
      <link>https://communities.sas.com/t5/Statistical-Procedures/PS-Fine-Stratification-in-SAS/m-p/984119#M49300</link>
      <description>&lt;P&gt;Hello, everyone&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;P&gt;Today I read a paper which used the&amp;nbsp;PS Fine Stratification as their statistical analysis method. It was inspiring as the IPTW method can inflate the pseudo-cohort by outliers (by extreme low/high propensity scores). I know the robust variance estimator can handle the correlation between clone observations but the inflation itself can affect the accuracy of the confidence intervals.&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;P&gt;By the method of&amp;nbsp;PS Fine Stratification, the IPTW-based inflation is not a problem as it will not use a pseudo-cohort. Therefore, I wonder if we can do&amp;nbsp;PS Fine Stratification in SAS by existing syntaxes. Thank you.&lt;/P&gt;</description>
      <pubDate>Thu, 26 Feb 2026 08:20:22 GMT</pubDate>
      <guid>https://communities.sas.com/t5/Statistical-Procedures/PS-Fine-Stratification-in-SAS/m-p/984119#M49300</guid>
      <dc:creator>TomHsiung</dc:creator>
      <dc:date>2026-02-26T08:20:22Z</dc:date>
    </item>
    <item>
      <title>Re: PS Fine Stratification in SAS</title>
      <link>https://communities.sas.com/t5/Statistical-Procedures/PS-Fine-Stratification-in-SAS/m-p/984169#M49303</link>
      <description>&lt;P&gt;Two resource suggestions:&lt;/P&gt;
&lt;UL&gt;
&lt;LI&gt;Ask the Expert webinar on the PSMATCH procedure:&amp;nbsp;&lt;A href="https://communities.sas.com/t5/Ask-the-Expert/I-Have-Results-From-PROC-PSMATCH-Now-What-Q-amp-A-Slides-and-On/ta-p/968294" target="_blank"&gt;I Have Results From PROC PSMATCH. Now What? Q&amp;amp;A, Slides, and On-Demand... - SAS Support Communities&lt;/A&gt;&lt;/LI&gt;
&lt;LI&gt;Description of weights in the PSMATCH documentation:&amp;nbsp;&lt;A href="https://go.documentation.sas.com/doc/en/pgmsascdc/v_072/statug/statug_psmatch_details05.htm#statug.psmatch.psmattwgt" target="_blank"&gt;SAS Help Center: Propensity Score Weighting&lt;/A&gt;&lt;/LI&gt;
&lt;/UL&gt;</description>
      <pubDate>Thu, 26 Feb 2026 16:56:46 GMT</pubDate>
      <guid>https://communities.sas.com/t5/Statistical-Procedures/PS-Fine-Stratification-in-SAS/m-p/984169#M49303</guid>
      <dc:creator>JackieJ_SAS</dc:creator>
      <dc:date>2026-02-26T16:56:46Z</dc:date>
    </item>
  </channel>
</rss>

