<?xml version="1.0" encoding="UTF-8"?><!-- generator="wordpress/2.3.2" -->
<rss version="2.0"
	xmlns:content="http://purl.org/rss/1.0/modules/content/"
	xmlns:dc="http://purl.org/dc/elements/1.1/"
	>
<channel>
	<title>Comments on: Excellent feedback so far and some answers to your questions!</title>
	<link>http://blog.webanalyticsdemystified.com/weblog/2005/07/excellent-feedback-so-far-and-some.html</link>
	<description>Eric T. Peterson's Web Analytics Demystified weblog, since 2005!</description>
	<pubDate>Fri, 21 Nov 2008 03:43:36 +0000</pubDate>
	<generator>http://wordpress.org/?v=2.3.2</generator>
		<item>
		<title>By: Phil Aaronson</title>
		<link>http://blog.webanalyticsdemystified.com/weblog/2005/07/excellent-feedback-so-far-and-some.html#comment-17</link>
		<dc:creator>Phil Aaronson</dc:creator>
		<pubDate>Wed, 20 Jul 2005 03:23:00 +0000</pubDate>
		<guid>http://blog.webanalyticsdemystified.com/weblog/2005/07/excellent-feedback-so-far-and-some.html#comment-17</guid>
		<description>Median, for a lot of distributions won't help much (... and all that sorting). Chances are pretty good that there's a huge tail here and the median value will be 1.&lt;BR/&gt;&lt;BR/&gt;A better indicator might be the % of 1 page visits?</description>
		<content:encoded><![CDATA[<p>Median, for a lot of distributions won&#8217;t help much (&#8230; and all that sorting). Chances are pretty good that there&#8217;s a huge tail here and the median value will be 1.</p>
<p>A better indicator might be the % of 1 page visits?</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Jerry Hosking</title>
		<link>http://blog.webanalyticsdemystified.com/weblog/2005/07/excellent-feedback-so-far-and-some.html#comment-18</link>
		<dc:creator>Jerry Hosking</dc:creator>
		<pubDate>Thu, 14 Jul 2005 10:20:00 +0000</pubDate>
		<guid>http://blog.webanalyticsdemystified.com/weblog/2005/07/excellent-feedback-so-far-and-some.html#comment-18</guid>
		<description>Does anyone have a simple strategy for calculating the median value for indicators like these?&lt;BR/&gt;&lt;BR/&gt;Median Pages Viewed per Visit = (n visits + 1)/2th ranked pages viewed values&lt;BR/&gt;&lt;BR/&gt;Well, I guess it's not presented sufficiently simply if you still have to explain it.&lt;BR/&gt;&lt;BR/&gt;I can do it, I just don't know how to write it down.&lt;BR/&gt;&lt;BR/&gt;- Find number of visits for time period&lt;BR/&gt;&lt;BR/&gt;- Add one&lt;BR/&gt;&lt;BR/&gt;- Divide by 2&lt;BR/&gt;&lt;BR/&gt;- Sort values for pages viewed in each visit (descending)&lt;BR/&gt;&lt;BR/&gt;- Choose nth value from the sorted value list where n is the result of (number of visits +1)/2&lt;BR/&gt;&lt;BR/&gt;Of course, this is just the simplest of median calculation methods.  Others get more complex depending on the data.&lt;BR/&gt;&lt;BR/&gt;Don't know if this will help, but it might give you an idea to build on.&lt;BR/&gt;&lt;BR/&gt;Jerry</description>
		<content:encoded><![CDATA[<p>Does anyone have a simple strategy for calculating the median value for indicators like these?</p>
<p>Median Pages Viewed per Visit = (n visits + 1)/2th ranked pages viewed values</p>
<p>Well, I guess it&#8217;s not presented sufficiently simply if you still have to explain it.</p>
<p>I can do it, I just don&#8217;t know how to write it down.</p>
<p>- Find number of visits for time period</p>
<p>- Add one</p>
<p>- Divide by 2</p>
<p>- Sort values for pages viewed in each visit (descending)</p>
<p>- Choose nth value from the sorted value list where n is the result of (number of visits +1)/2</p>
<p>Of course, this is just the simplest of median calculation methods.  Others get more complex depending on the data.</p>
<p>Don&#8217;t know if this will help, but it might give you an idea to build on.</p>
<p>Jerry</p>
]]></content:encoded>
	</item>
</channel>
</rss>
