<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"
	xmlns:content="http://purl.org/rss/1.0/modules/content/"
	xmlns:dc="http://purl.org/dc/elements/1.1/"
	xmlns:atom="http://www.w3.org/2005/Atom"
	xmlns:sy="http://purl.org/rss/1.0/modules/syndication/"
		>
<channel>
	<title>Comments on: Rogue Statisticians</title>
	<atom:link href="http://www.overheardinprovidence.com/2008/02/11/rogue-statisticians/feed/" rel="self" type="application/rss+xml" />
	<link>http://www.overheardinprovidence.com/2008/02/11/rogue-statisticians/</link>
	<description>A blog by EERac</description>
	<lastBuildDate>Sat, 07 Jan 2012 06:46:19 +0000</lastBuildDate>
	<generator>http://wordpress.org/?v=2.9.2</generator>
	<sy:updatePeriod>hourly</sy:updatePeriod>
	<sy:updateFrequency>1</sy:updateFrequency>
		<item>
		<title>By: EERac</title>
		<link>http://www.overheardinprovidence.com/2008/02/11/rogue-statisticians/comment-page-1/#comment-190</link>
		<dc:creator>EERac</dc:creator>
		<pubDate>Thu, 14 Feb 2008 23:42:38 +0000</pubDate>
		<guid isPermaLink="false">http://www.overheardinprovidence.com/2008/02/11/rogue-statisticians/#comment-190</guid>
		<description>Drew, that&#039;s a good point. I only used a quadratic because that&#039;s what the professors used, but the choice clearly biases the curve to divide a pitcher&#039;s career into &quot;two phases&quot;. Looking at the actual data, and the image you posted, a higher degree polynomial is probably more appropriate. Unfortunately, to get the three phase behavior you&#039;ve suggested, a polynomial of at least degree six is required. I just tried this, but it didn&#039;t reveal much. It was basically overfitting the data.</description>
		<content:encoded><![CDATA[<p>Drew, that&#8217;s a good point. I only used a quadratic because that&#8217;s what the professors used, but the choice clearly biases the curve to divide a pitcher&#8217;s career into &#8220;two phases&#8221;. Looking at the actual data, and the image you posted, a higher degree polynomial is probably more appropriate. Unfortunately, to get the three phase behavior you&#8217;ve suggested, a polynomial of at least degree six is required. I just tried this, but it didn&#8217;t reveal much. It was basically overfitting the data.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Drew</title>
		<link>http://www.overheardinprovidence.com/2008/02/11/rogue-statisticians/comment-page-1/#comment-189</link>
		<dc:creator>Drew</dc:creator>
		<pubDate>Thu, 14 Feb 2008 18:23:22 +0000</pubDate>
		<guid isPermaLink="false">http://www.overheardinprovidence.com/2008/02/11/rogue-statisticians/#comment-189</guid>
		<description>Sorry, the quadratic doesn&#039;t cut it in the era.&#160; WHIP is obviously the same. At least three phases, which shoots down the theory that statistics support a simple drug use pattern.

http://img197.imagevenue.com/img.php?image=12578_clemens_era_122_527lo.jpg</description>
		<content:encoded><![CDATA[<p>Sorry, the quadratic doesn&#8217;t cut it in the era.&nbsp; WHIP is obviously the same. At least three phases, which shoots down the theory that statistics support a simple drug use pattern.</p>
<p><a href="http://img197.imagevenue.com/img.php?image=12578_clemens_era_122_527lo.jpg" rel="nofollow" onclick="javascript:urchinTracker ('/outbound/comment/img197.imagevenue.com');">http://img197.imagevenue.com/img.php?image=12578_clemens_era_122_527lo.jpg</a></p>
]]></content:encoded>
	</item>
</channel>
</rss>

