<?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 proc surveyfreq question about strata in Statistical Procedures</title>
    <link>https://communities.sas.com/t5/Statistical-Procedures/proc-surveyfreq-question-about-strata/m-p/315609#M16633</link>
    <description>&lt;P&gt;Hi.&lt;/P&gt;&lt;P&gt;I'm using SAS 9.4.&lt;/P&gt;&lt;P&gt;I’d like to compare the answers to a survey where two different sampling approaches were used to sample the same population.&amp;nbsp; Each approach asked the respondents to complete the same survey.&amp;nbsp; The first approach used a stratified random sample to sample the population and the second approach used a nonprobability sample.&amp;nbsp; The questions on the surveys are exactly the same and the respondents were surveyed at the same time.&amp;nbsp; Questions on the survey generally asked the respondents their satisfaction level (usually 4-5 levels) or whether they favored or opposed certain issues related to transportation.&amp;nbsp; Weights were created for both of the approaches (finalwt).&amp;nbsp;&lt;/P&gt;&lt;P&gt;&lt;BR /&gt;The stratified random sample has 5 strata (5 districts which are labeled 1-5 in a variable called district).&amp;nbsp; The nonprobability sample was not stratified so I created a variable called district which contains all 6's.&amp;nbsp; There is an indicator variable named ind which is 1 for the non probability sample and 2 for the stratified sample.&amp;nbsp; The dataset is called panelprob.&amp;nbsp; The example below shows how I compared the two samples for one of the questions on the survey (Q3). The code works fine.&amp;nbsp;&lt;/P&gt;&lt;P&gt;&lt;BR /&gt;proc surveyfreq data= panelprob;&lt;BR /&gt;&amp;nbsp; &amp;nbsp; &amp;nbsp; tables&amp;nbsp; ind * Q3/CHISQ ROW NOSTD NOCELLPERCENT;&lt;BR /&gt;&amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; strata&amp;nbsp; district;&lt;BR /&gt;&amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; weight&amp;nbsp; finalwt;&lt;BR /&gt;run;&lt;BR /&gt;&lt;BR /&gt;My question is:&amp;nbsp; Have set up the strata correctly? &amp;nbsp;Thank you.&lt;BR /&gt;&lt;/P&gt;</description>
    <pubDate>Wed, 30 Nov 2016 16:58:00 GMT</pubDate>
    <dc:creator>Jeannie</dc:creator>
    <dc:date>2016-11-30T16:58:00Z</dc:date>
    <item>
      <title>proc surveyfreq question about strata</title>
      <link>https://communities.sas.com/t5/Statistical-Procedures/proc-surveyfreq-question-about-strata/m-p/315609#M16633</link>
      <description>&lt;P&gt;Hi.&lt;/P&gt;&lt;P&gt;I'm using SAS 9.4.&lt;/P&gt;&lt;P&gt;I’d like to compare the answers to a survey where two different sampling approaches were used to sample the same population.&amp;nbsp; Each approach asked the respondents to complete the same survey.&amp;nbsp; The first approach used a stratified random sample to sample the population and the second approach used a nonprobability sample.&amp;nbsp; The questions on the surveys are exactly the same and the respondents were surveyed at the same time.&amp;nbsp; Questions on the survey generally asked the respondents their satisfaction level (usually 4-5 levels) or whether they favored or opposed certain issues related to transportation.&amp;nbsp; Weights were created for both of the approaches (finalwt).&amp;nbsp;&lt;/P&gt;&lt;P&gt;&lt;BR /&gt;The stratified random sample has 5 strata (5 districts which are labeled 1-5 in a variable called district).&amp;nbsp; The nonprobability sample was not stratified so I created a variable called district which contains all 6's.&amp;nbsp; There is an indicator variable named ind which is 1 for the non probability sample and 2 for the stratified sample.&amp;nbsp; The dataset is called panelprob.&amp;nbsp; The example below shows how I compared the two samples for one of the questions on the survey (Q3). The code works fine.&amp;nbsp;&lt;/P&gt;&lt;P&gt;&lt;BR /&gt;proc surveyfreq data= panelprob;&lt;BR /&gt;&amp;nbsp; &amp;nbsp; &amp;nbsp; tables&amp;nbsp; ind * Q3/CHISQ ROW NOSTD NOCELLPERCENT;&lt;BR /&gt;&amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; strata&amp;nbsp; district;&lt;BR /&gt;&amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp; weight&amp;nbsp; finalwt;&lt;BR /&gt;run;&lt;BR /&gt;&lt;BR /&gt;My question is:&amp;nbsp; Have set up the strata correctly? &amp;nbsp;Thank you.&lt;BR /&gt;&lt;/P&gt;</description>
      <pubDate>Wed, 30 Nov 2016 16:58:00 GMT</pubDate>
      <guid>https://communities.sas.com/t5/Statistical-Procedures/proc-surveyfreq-question-about-strata/m-p/315609#M16633</guid>
      <dc:creator>Jeannie</dc:creator>
      <dc:date>2016-11-30T16:58:00Z</dc:date>
    </item>
    <item>
      <title>Re: proc surveyfreq question about strata</title>
      <link>https://communities.sas.com/t5/Statistical-Procedures/proc-surveyfreq-question-about-strata/m-p/317752#M16726</link>
      <description>&lt;P&gt;The type of non -probability sample you drew might make a difference to the answer. What type was it?&lt;/P&gt;</description>
      <pubDate>Fri, 09 Dec 2016 00:28:12 GMT</pubDate>
      <guid>https://communities.sas.com/t5/Statistical-Procedures/proc-surveyfreq-question-about-strata/m-p/317752#M16726</guid>
      <dc:creator>Damien_Mather</dc:creator>
      <dc:date>2016-12-09T00:28:12Z</dc:date>
    </item>
    <item>
      <title>Re: proc surveyfreq question about strata</title>
      <link>https://communities.sas.com/t5/Statistical-Procedures/proc-surveyfreq-question-about-strata/m-p/318345#M16791</link>
      <description>&lt;P&gt;It was a panel sample where the individuals needed to fufill certain criteria (e.g., adults in a certain state).&lt;/P&gt;</description>
      <pubDate>Mon, 12 Dec 2016 18:28:36 GMT</pubDate>
      <guid>https://communities.sas.com/t5/Statistical-Procedures/proc-surveyfreq-question-about-strata/m-p/318345#M16791</guid>
      <dc:creator>Jeannie</dc:creator>
      <dc:date>2016-12-12T18:28:36Z</dc:date>
    </item>
  </channel>
</rss>

