<?xml version="1.0" encoding="utf-8"?>
<rss version="2.0"><channel><title>Disqus - Latest Comments for hadley</title><link>http://disqus.com/people/hadley/</link><description></description><language>en</language><lastBuildDate>Sun, 16 Nov 2008 12:55:48 -0000</lastBuildDate><item><title>Re: Statistical Analysis and A/B Testing</title><link>http://20bits.disqus.com/statistical_analysis_and_ab_testing/#comment-3806937</link><description>"The conversion rate for each treatment approximates a normally distributed random variable" is more correct.</description><dc:creator xmlns:dc="http://purl.org/dc/elements/1.1/">jfarmer</dc:creator><pubDate>Sun, 16 Nov 2008 12:55:48 -0000</pubDate></item><item><title>Re: Statistical Analysis and A/B Testing</title><link>http://20bits.disqus.com/statistical_analysis_and_ab_testing/#comment-3803473</link><description>"The conversion rate for each treatment is a normally distributed random variable" - are you sure??</description><dc:creator xmlns:dc="http://purl.org/dc/elements/1.1/">hadley</dc:creator><pubDate>Sun, 16 Nov 2008 10:40:34 -0000</pubDate></item><item><title>Re: Statistical Analysis and A/B Testing</title><link>http://20bits.disqus.com/statistical_analysis_and_ab_testing/#comment-3803427</link><description>If you're going to use R, why not actually use the appropriate test - in this case it would be prop.test() for testing the different between two proportions.</description><dc:creator xmlns:dc="http://purl.org/dc/elements/1.1/">hadley</dc:creator><pubDate>Sun, 16 Nov 2008 10:39:32 -0000</pubDate></item><item><title>Re: idea: a machine that eats dirt and prints roads</title><link>http://andrei-shindyapin.disqus.com/idea_a_machine_that_eats_dirt_and_prints_roads/#comment-2025711</link><description>See &lt;a href="http://www.youtube.com/watch?v=f28_zrU0X4A" rel="nofollow"&gt;http://www.youtube.com/watch?v=f28_zrU0X4A&lt;/a&gt; for the complete set up ;)</description><dc:creator xmlns:dc="http://purl.org/dc/elements/1.1/">hadley</dc:creator><pubDate>Tue, 02 Sep 2008 22:58:09 -0000</pubDate></item></channel></rss>