<?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: How to make a specific type of table/matrix to compare confidence interval bounds across categor in Statistical Procedures</title>
    <link>https://communities.sas.com/t5/Statistical-Procedures/How-to-make-a-specific-type-of-table-matrix-to-compare/m-p/409746#M21384</link>
    <description>&lt;P&gt;The name you are searching for is "multiple comparisons of means."&amp;nbsp; The GLM procedure can do it. There are examples in the doc. I suggest using a Tukey-Kramer adjustment and visualizing the differences in means by using the 'diffogram', as explained in the article &lt;A href="https://blogs.sas.com/content/iml/2017/10/18/diffogram-multiple-comparisons-sas.html" target="_self"&gt;"The diffogram and other graphs for multiple comparisons of means."&lt;/A&gt;&lt;/P&gt;</description>
    <pubDate>Thu, 02 Nov 2017 09:43:14 GMT</pubDate>
    <dc:creator>Rick_SAS</dc:creator>
    <dc:date>2017-11-02T09:43:14Z</dc:date>
    <item>
      <title>How to make a specific type of table/matrix to compare confidence interval bounds across categories</title>
      <link>https://communities.sas.com/t5/Statistical-Procedures/How-to-make-a-specific-type-of-table-matrix-to-compare/m-p/409224#M21383</link>
      <description>&lt;P&gt;Currently, I have several confidence intervals across categorical variables under several broader categories. Here's a simplified version of the data to better explain the situation:&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;Suppose my data set is work.ci_out:&lt;/P&gt;&lt;TABLE&gt;&lt;TBODY&gt;&lt;TR&gt;&lt;TD&gt;&lt;STRONG&gt;Type&lt;/STRONG&gt;&lt;/TD&gt;&lt;TD&gt;&lt;STRONG&gt;Category&lt;/STRONG&gt;&lt;/TD&gt;&lt;TD&gt;&lt;STRONG&gt;Mean&lt;/STRONG&gt;&lt;/TD&gt;&lt;TD&gt;&lt;STRONG&gt;CI_LB&lt;/STRONG&gt;&lt;/TD&gt;&lt;TD&gt;&lt;STRONG&gt;CI_UB&lt;/STRONG&gt;&lt;/TD&gt;&lt;/TR&gt;&lt;TR&gt;&lt;TD&gt;1&lt;/TD&gt;&lt;TD&gt;A&lt;/TD&gt;&lt;TD&gt;50.90%&lt;/TD&gt;&lt;TD&gt;49.48%&lt;/TD&gt;&lt;TD&gt;52.32%&lt;/TD&gt;&lt;/TR&gt;&lt;TR&gt;&lt;TD&gt;1&lt;/TD&gt;&lt;TD&gt;B&lt;/TD&gt;&lt;TD&gt;52.25%&lt;/TD&gt;&lt;TD&gt;50.94%&lt;/TD&gt;&lt;TD&gt;53.56%&lt;/TD&gt;&lt;/TR&gt;&lt;TR&gt;&lt;TD&gt;1&lt;/TD&gt;&lt;TD&gt;C&lt;/TD&gt;&lt;TD&gt;58.62%&lt;/TD&gt;&lt;TD&gt;57.47%&lt;/TD&gt;&lt;TD&gt;59.77%&lt;/TD&gt;&lt;/TR&gt;&lt;TR&gt;&lt;TD&gt;1&lt;/TD&gt;&lt;TD&gt;D&lt;/TD&gt;&lt;TD&gt;45.73%&lt;/TD&gt;&lt;TD&gt;44.61%&lt;/TD&gt;&lt;TD&gt;46.85%&lt;/TD&gt;&lt;/TR&gt;&lt;TR&gt;&lt;TD&gt;1&lt;/TD&gt;&lt;TD&gt;E&lt;/TD&gt;&lt;TD&gt;55.13%&lt;/TD&gt;&lt;TD&gt;54.04%&lt;/TD&gt;&lt;TD&gt;56.22%&lt;/TD&gt;&lt;/TR&gt;&lt;TR&gt;&lt;TD&gt;1&lt;/TD&gt;&lt;TD&gt;F&lt;/TD&gt;&lt;TD&gt;59.43%&lt;/TD&gt;&lt;TD&gt;58.33%&lt;/TD&gt;&lt;TD&gt;60.53%&lt;/TD&gt;&lt;/TR&gt;&lt;TR&gt;&lt;TD&gt;2&lt;/TD&gt;&lt;TD&gt;A&lt;/TD&gt;&lt;TD&gt;54.82%&lt;/TD&gt;&lt;TD&gt;52.24%&lt;/TD&gt;&lt;TD&gt;57.40%&lt;/TD&gt;&lt;/TR&gt;&lt;TR&gt;&lt;TD&gt;2&lt;/TD&gt;&lt;TD&gt;B&lt;/TD&gt;&lt;TD&gt;61.85%&lt;/TD&gt;&lt;TD&gt;59.43%&lt;/TD&gt;&lt;TD&gt;64.26%&lt;/TD&gt;&lt;/TR&gt;&lt;TR&gt;&lt;TD&gt;2&lt;/TD&gt;&lt;TD&gt;C&lt;/TD&gt;&lt;TD&gt;66.23%&lt;/TD&gt;&lt;TD&gt;63.91%&lt;/TD&gt;&lt;TD&gt;68.54%&lt;/TD&gt;&lt;/TR&gt;&lt;TR&gt;&lt;TD&gt;2&lt;/TD&gt;&lt;TD&gt;D&lt;/TD&gt;&lt;TD&gt;51.53%&lt;/TD&gt;&lt;TD&gt;49.23%&lt;/TD&gt;&lt;TD&gt;53.84%&lt;/TD&gt;&lt;/TR&gt;&lt;TR&gt;&lt;TD&gt;2&lt;/TD&gt;&lt;TD&gt;E&lt;/TD&gt;&lt;TD&gt;57.74%&lt;/TD&gt;&lt;TD&gt;55.36%&lt;/TD&gt;&lt;TD&gt;60.11%&lt;/TD&gt;&lt;/TR&gt;&lt;TR&gt;&lt;TD&gt;2&lt;/TD&gt;&lt;TD&gt;F&lt;/TD&gt;&lt;TD&gt;61.14%&lt;/TD&gt;&lt;TD&gt;58.72%&lt;/TD&gt;&lt;TD&gt;63.56%&lt;/TD&gt;&lt;/TR&gt;&lt;/TBODY&gt;&lt;/TABLE&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;What I would like to do is&amp;nbsp;to create a table/matrix output that compares the CI upper bounds against the CI lower bounds and flags any pairings (under a Type) where the upper bound is less than the lower bound, i.e., where there is a significant difference. The output would look something like this:&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;&lt;span class="lia-inline-image-display-wrapper lia-image-align-inline" image-alt="image.png" style="width: 400px;"&gt;&lt;img src="https://communities.sas.com/t5/image/serverpage/image-id/16360i311823968A1BDDDD/image-size/medium?v=v2&amp;amp;px=400" role="button" title="image.png" alt="image.png" /&gt;&lt;/span&gt;&lt;/P&gt;&lt;P&gt;Not sure if this type of an output already has a name. Either way, these matrices flag the category pairs where the CI Upper Bound is less than the CI Lower Bound. Obviously, the diagonals would always be empty, but with this&amp;nbsp;table, we can quickly see which categories are significantly smaller than others.&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;The other subtle thing I would like to be able to do is to have separate matrices for different Types, as pictured above.&amp;nbsp;&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;The confidence interval data&amp;nbsp;is currently sitting in a SAS data set that looks a lot like the first table. A colleague suggested I use arrays to do this, but I have been struggling mightily with this since I am not the most proficient at SAS. Any help would be greatly appreciated.&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;Thanks!&lt;/P&gt;</description>
      <pubDate>Tue, 31 Oct 2017 17:59:21 GMT</pubDate>
      <guid>https://communities.sas.com/t5/Statistical-Procedures/How-to-make-a-specific-type-of-table-matrix-to-compare/m-p/409224#M21383</guid>
      <dc:creator>shea_poaa</dc:creator>
      <dc:date>2017-10-31T17:59:21Z</dc:date>
    </item>
    <item>
      <title>Re: How to make a specific type of table/matrix to compare confidence interval bounds across categor</title>
      <link>https://communities.sas.com/t5/Statistical-Procedures/How-to-make-a-specific-type-of-table-matrix-to-compare/m-p/409746#M21384</link>
      <description>&lt;P&gt;The name you are searching for is "multiple comparisons of means."&amp;nbsp; The GLM procedure can do it. There are examples in the doc. I suggest using a Tukey-Kramer adjustment and visualizing the differences in means by using the 'diffogram', as explained in the article &lt;A href="https://blogs.sas.com/content/iml/2017/10/18/diffogram-multiple-comparisons-sas.html" target="_self"&gt;"The diffogram and other graphs for multiple comparisons of means."&lt;/A&gt;&lt;/P&gt;</description>
      <pubDate>Thu, 02 Nov 2017 09:43:14 GMT</pubDate>
      <guid>https://communities.sas.com/t5/Statistical-Procedures/How-to-make-a-specific-type-of-table-matrix-to-compare/m-p/409746#M21384</guid>
      <dc:creator>Rick_SAS</dc:creator>
      <dc:date>2017-11-02T09:43:14Z</dc:date>
    </item>
    <item>
      <title>Re: How to make a specific type of table/matrix to compare confidence interval bounds across categor</title>
      <link>https://communities.sas.com/t5/Statistical-Procedures/How-to-make-a-specific-type-of-table-matrix-to-compare/m-p/409910#M21406</link>
      <description>Those plots are great! I'll give them a shot. Thanks for your help and putting a name to the concept.</description>
      <pubDate>Thu, 02 Nov 2017 16:20:55 GMT</pubDate>
      <guid>https://communities.sas.com/t5/Statistical-Procedures/How-to-make-a-specific-type-of-table-matrix-to-compare/m-p/409910#M21406</guid>
      <dc:creator>shea_poaa</dc:creator>
      <dc:date>2017-11-02T16:20:55Z</dc:date>
    </item>
  </channel>
</rss>

