<?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: a question about confidengce interval in Statistical Procedures</title>
    <link>https://communities.sas.com/t5/Statistical-Procedures/a-question-about-confidengce-interval/m-p/775844#M37989</link>
    <description>&lt;P&gt;Means are continuous and scaled between negative infinity and positive infinity. There's no reason a mean (or a confidence interval for a mean) can't be less than zero.&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;P&gt;Proportions are continuous but scaled between 0 and 1. Proportions (and confidence intervals for proportions) cannot be less than 0. You want to have SAS compute proportions, not means. To compute proportions, use PROC SURVEYFREQ.&lt;/P&gt;</description>
    <pubDate>Fri, 22 Oct 2021 10:46:08 GMT</pubDate>
    <dc:creator>PaigeMiller</dc:creator>
    <dc:date>2021-10-22T10:46:08Z</dc:date>
    <item>
      <title>a question about confidengce interval</title>
      <link>https://communities.sas.com/t5/Statistical-Procedures/a-question-about-confidengce-interval/m-p/775811#M37987</link>
      <description>&lt;P&gt;Hello, I am a novice in SAS analysis. When using SAS to analyze complex sampling data, I found that when some proportions are small or large, the confidence interval is less than 0 or greater than 1, which is obviously impossible. Below is my code. What can I do to solve it? Drcat is a binary variable. I want to count its prevalence and confidence interval in the target population.&lt;/P&gt;&lt;P&gt;thank you !!!!!!!!!!!!&lt;/P&gt;&lt;PRE&gt;proc surveymeans data=allcomcat99 nomcar VARMETHOD=TAYLOR ;
stratum sdmvstra;cluster sdmvpsu; class agegroup;
var drcat;
domain sub sel;
weight wtmec2yr;
title "dr prevanlence";
run;&lt;/PRE&gt;</description>
      <pubDate>Fri, 22 Oct 2021 05:53:29 GMT</pubDate>
      <guid>https://communities.sas.com/t5/Statistical-Procedures/a-question-about-confidengce-interval/m-p/775811#M37987</guid>
      <dc:creator>liiiiiiiib</dc:creator>
      <dc:date>2021-10-22T05:53:29Z</dc:date>
    </item>
    <item>
      <title>Re: a question about confidengce interval</title>
      <link>https://communities.sas.com/t5/Statistical-Procedures/a-question-about-confidengce-interval/m-p/775844#M37989</link>
      <description>&lt;P&gt;Means are continuous and scaled between negative infinity and positive infinity. There's no reason a mean (or a confidence interval for a mean) can't be less than zero.&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;P&gt;Proportions are continuous but scaled between 0 and 1. Proportions (and confidence intervals for proportions) cannot be less than 0. You want to have SAS compute proportions, not means. To compute proportions, use PROC SURVEYFREQ.&lt;/P&gt;</description>
      <pubDate>Fri, 22 Oct 2021 10:46:08 GMT</pubDate>
      <guid>https://communities.sas.com/t5/Statistical-Procedures/a-question-about-confidengce-interval/m-p/775844#M37989</guid>
      <dc:creator>PaigeMiller</dc:creator>
      <dc:date>2021-10-22T10:46:08Z</dc:date>
    </item>
  </channel>
</rss>

