<?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: Tip: How to compute percentiles (quantiles) in SAS Programming</title>
    <link>https://communities.sas.com/t5/SAS-Programming/Tip-How-to-compute-percentiles-quantiles/m-p/328104#M73235</link>
    <description>&lt;P&gt;If you want to assign each value an integer (the percentile) between 0 and 99, you can use PROC RANK with GROUPS=100.&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;PRE&gt;&lt;CODE class=" language-sas"&gt;proc rank data=a groups=100 out=Pctls;
var x;
ranks pctl;
run;&lt;/CODE&gt;&lt;/PRE&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;P&gt;The PCTLS data set contains the original variable and the corresponding percentiles.&lt;/P&gt;</description>
    <pubDate>Fri, 27 Jan 2017 19:37:37 GMT</pubDate>
    <dc:creator>Rick_SAS</dc:creator>
    <dc:date>2017-01-27T19:37:37Z</dc:date>
    <item>
      <title>Tip: How to compute percentiles (quantiles)</title>
      <link>https://communities.sas.com/t5/SAS-Programming/Tip-How-to-compute-percentiles-quantiles/m-p/328101#M73233</link>
      <description>&lt;P&gt;I have a set of data. I want to compute the percentiles of each data point in the whole data set. for example, what is the percentile of data point 11326.21369 in the data set? The below is part of&amp;nbsp;my data.&lt;/P&gt;&lt;P&gt;&amp;nbsp; Cost&lt;/P&gt;&lt;P&gt;11326.210369&lt;BR /&gt;12486.48938&lt;BR /&gt;12461.600695&lt;BR /&gt;17078.181683&lt;BR /&gt;20830.827535&lt;BR /&gt;21301.654723&lt;BR /&gt;19246.458983&lt;BR /&gt;17233.110851&lt;BR /&gt;20086.991101&lt;BR /&gt;18998.225999&lt;BR /&gt;18755.580299&lt;BR /&gt;18363.870699&lt;BR /&gt;18084.353599&lt;BR /&gt;22674.720499&lt;BR /&gt;16680.130049&lt;BR /&gt;15838.031999&lt;BR /&gt;19773.713649&lt;BR /&gt;16864.323849&lt;BR /&gt;17499.784599&lt;BR /&gt;16918.186999&lt;BR /&gt;18383.525249&lt;BR /&gt;20307.965549&lt;BR /&gt;18135.335899&lt;BR /&gt;16504.779198&lt;BR /&gt;22346.398306&lt;BR /&gt;18484.330644&lt;BR /&gt;18335.447644&lt;BR /&gt;19685.665094&lt;BR /&gt;19591.907594&lt;BR /&gt;18702.066744&lt;BR /&gt;18938.583444&lt;BR /&gt;17878.801744&lt;BR /&gt;23398.002544&lt;BR /&gt;18101.282344&lt;BR /&gt;18554.513094&lt;BR /&gt;18812.566344&lt;BR /&gt;21834.429194&lt;BR /&gt;19587.505132&lt;BR /&gt;16619.15172&lt;/P&gt;</description>
      <pubDate>Fri, 27 Jan 2017 19:06:43 GMT</pubDate>
      <guid>https://communities.sas.com/t5/SAS-Programming/Tip-How-to-compute-percentiles-quantiles/m-p/328101#M73233</guid>
      <dc:creator>zhuxiaoyan1</dc:creator>
      <dc:date>2017-01-27T19:06:43Z</dc:date>
    </item>
    <item>
      <title>Re: Tip: How to compute percentiles (quantiles)</title>
      <link>https://communities.sas.com/t5/SAS-Programming/Tip-How-to-compute-percentiles-quantiles/m-p/328103#M73234</link>
      <description>&lt;P&gt;Easiest might be to use PROC RANK. e.g.:&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;PRE&gt;proc rank data=have out=want  groups=100;
  var cost;
  ranks cost_rank;
run;
&lt;/PRE&gt;
&lt;P&gt;If you want quantiles just change the groups=100 option to groups=5.&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;P&gt;HTH,&lt;/P&gt;
&lt;P&gt;Art, CEO, AnalystFinder.com&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;</description>
      <pubDate>Fri, 27 Jan 2017 19:33:29 GMT</pubDate>
      <guid>https://communities.sas.com/t5/SAS-Programming/Tip-How-to-compute-percentiles-quantiles/m-p/328103#M73234</guid>
      <dc:creator>art297</dc:creator>
      <dc:date>2017-01-27T19:33:29Z</dc:date>
    </item>
    <item>
      <title>Re: Tip: How to compute percentiles (quantiles)</title>
      <link>https://communities.sas.com/t5/SAS-Programming/Tip-How-to-compute-percentiles-quantiles/m-p/328104#M73235</link>
      <description>&lt;P&gt;If you want to assign each value an integer (the percentile) between 0 and 99, you can use PROC RANK with GROUPS=100.&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;PRE&gt;&lt;CODE class=" language-sas"&gt;proc rank data=a groups=100 out=Pctls;
var x;
ranks pctl;
run;&lt;/CODE&gt;&lt;/PRE&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;P&gt;The PCTLS data set contains the original variable and the corresponding percentiles.&lt;/P&gt;</description>
      <pubDate>Fri, 27 Jan 2017 19:37:37 GMT</pubDate>
      <guid>https://communities.sas.com/t5/SAS-Programming/Tip-How-to-compute-percentiles-quantiles/m-p/328104#M73235</guid>
      <dc:creator>Rick_SAS</dc:creator>
      <dc:date>2017-01-27T19:37:37Z</dc:date>
    </item>
  </channel>
</rss>

