<?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: Two sample t test with a raw dataset in Statistical Procedures</title>
    <link>https://communities.sas.com/t5/Statistical-Procedures/Two-sample-t-test-with-a-raw-dataset/m-p/46054#M2022</link>
    <description>&amp;gt; I have a raw dataset of a bunch of cereals and many&lt;BR /&gt;
&amp;gt; other variables of them. One variable is the&lt;BR /&gt;
&amp;gt; manufacturer, so that column is sorted into K, G, B,&lt;BR /&gt;
&amp;gt; etc. (The variable for each manufacturer). I have&lt;BR /&gt;
&amp;gt; another variable of fat. I need to test the&lt;BR /&gt;
&amp;gt; hypothesis that General Mills (G) has a higher fat&lt;BR /&gt;
&amp;gt; content than Kellogs (K). How would I do this? I know&lt;BR /&gt;
&amp;gt; I need to use the ttest procedure, but I don't know&lt;BR /&gt;
&amp;gt; how. Please note I only have to compare the fat&lt;BR /&gt;
&amp;gt; contents of those two manufacturers, which are&lt;BR /&gt;
&amp;gt; variables randomly in the dataset as well. Thanks.&lt;BR /&gt;
&lt;BR /&gt;
Assuming BRAND is the name of your cereal&lt;BR /&gt;
&lt;BR /&gt;
proc ttest data = mydata; &lt;BR /&gt;
 class brand;&lt;BR /&gt;
 var fat;&lt;BR /&gt;
 where brand = 'G' or brand = 'K';&lt;BR /&gt;
run;&lt;BR /&gt;
&lt;BR /&gt;
ought to work&lt;BR /&gt;
&lt;BR /&gt;
Peter</description>
    <pubDate>Mon, 25 Jan 2010 11:27:07 GMT</pubDate>
    <dc:creator>plf515</dc:creator>
    <dc:date>2010-01-25T11:27:07Z</dc:date>
    <item>
      <title>Two sample t test with a raw dataset</title>
      <link>https://communities.sas.com/t5/Statistical-Procedures/Two-sample-t-test-with-a-raw-dataset/m-p/46053#M2021</link>
      <description>I have a raw dataset of a bunch of cereals and many other variables of them. One variable is the manufacturer, so that column is sorted into K, G, B, etc. (The variable for each manufacturer). I have another variable of fat. I need to test the hypothesis that General Mills (G) has a higher fat content than Kellogs (K). How would I do this? I know I need to use the ttest procedure, but I don't know how. Please note I only have to compare the fat contents of those two manufacturers, which are variables randomly in the dataset as well. Thanks.</description>
      <pubDate>Sun, 24 Jan 2010 21:04:53 GMT</pubDate>
      <guid>https://communities.sas.com/t5/Statistical-Procedures/Two-sample-t-test-with-a-raw-dataset/m-p/46053#M2021</guid>
      <dc:creator>LordAlex</dc:creator>
      <dc:date>2010-01-24T21:04:53Z</dc:date>
    </item>
    <item>
      <title>Re: Two sample t test with a raw dataset</title>
      <link>https://communities.sas.com/t5/Statistical-Procedures/Two-sample-t-test-with-a-raw-dataset/m-p/46054#M2022</link>
      <description>&amp;gt; I have a raw dataset of a bunch of cereals and many&lt;BR /&gt;
&amp;gt; other variables of them. One variable is the&lt;BR /&gt;
&amp;gt; manufacturer, so that column is sorted into K, G, B,&lt;BR /&gt;
&amp;gt; etc. (The variable for each manufacturer). I have&lt;BR /&gt;
&amp;gt; another variable of fat. I need to test the&lt;BR /&gt;
&amp;gt; hypothesis that General Mills (G) has a higher fat&lt;BR /&gt;
&amp;gt; content than Kellogs (K). How would I do this? I know&lt;BR /&gt;
&amp;gt; I need to use the ttest procedure, but I don't know&lt;BR /&gt;
&amp;gt; how. Please note I only have to compare the fat&lt;BR /&gt;
&amp;gt; contents of those two manufacturers, which are&lt;BR /&gt;
&amp;gt; variables randomly in the dataset as well. Thanks.&lt;BR /&gt;
&lt;BR /&gt;
Assuming BRAND is the name of your cereal&lt;BR /&gt;
&lt;BR /&gt;
proc ttest data = mydata; &lt;BR /&gt;
 class brand;&lt;BR /&gt;
 var fat;&lt;BR /&gt;
 where brand = 'G' or brand = 'K';&lt;BR /&gt;
run;&lt;BR /&gt;
&lt;BR /&gt;
ought to work&lt;BR /&gt;
&lt;BR /&gt;
Peter</description>
      <pubDate>Mon, 25 Jan 2010 11:27:07 GMT</pubDate>
      <guid>https://communities.sas.com/t5/Statistical-Procedures/Two-sample-t-test-with-a-raw-dataset/m-p/46054#M2022</guid>
      <dc:creator>plf515</dc:creator>
      <dc:date>2010-01-25T11:27:07Z</dc:date>
    </item>
  </channel>
</rss>

