<?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: Lucky house prices</title>
	<atom:link href="http://www.johndcook.com/blog/2012/12/24/lucky-house-prices/feed/" rel="self" type="application/rss+xml" />
	<link>http://www.johndcook.com/blog/2012/12/24/lucky-house-prices/</link>
	<description>John D. Cook</description>
	<lastBuildDate>Wed, 22 May 2013 13:13:07 +0000</lastBuildDate>
	<sy:updatePeriod>hourly</sy:updatePeriod>
	<sy:updateFrequency>1</sy:updateFrequency>
	<generator>http://wordpress.org/?v=3.5.1</generator>
	<item>
		<title>By: Dave Tate</title>
		<link>http://www.johndcook.com/blog/2012/12/24/lucky-house-prices/comment-page-1/#comment-3957</link>
		<dc:creator>Dave Tate</dc:creator>
		<pubDate>Wed, 26 Dec 2012 20:08:22 +0000</pubDate>
		<guid isPermaLink="false">http://www.johndcook.com/blog/?p=12670#comment-3957</guid>
		<description><![CDATA[Deviations from uniformity (or from monotonicity, or other expected distributional shapes) can reveal important and otherwise-hidden processes.  My favorite example was when we were doing an independent assessment of a claims-processing organization.  Everyone we spoke with thought that the number of parts to a claim was an exogenous input -- until we showed them that the histogram of claims by number of parts had spikes at 8, 16, and 24.  It turns out that claim adjusters get double credit (in the company&#039;s idiotic work credit system) for claims with 8 or more parts; triple credit for 16 or more; etc.

The mechanisms by which adjusters can influence the number of parts, to bump 7 up to 8 or 15 up to 16, are weak and subtle -- but they are clearly being leveraged to maximum effect.]]></description>
		<content:encoded><![CDATA[<p>Deviations from uniformity (or from monotonicity, or other expected distributional shapes) can reveal important and otherwise-hidden processes.  My favorite example was when we were doing an independent assessment of a claims-processing organization.  Everyone we spoke with thought that the number of parts to a claim was an exogenous input &#8212; until we showed them that the histogram of claims by number of parts had spikes at 8, 16, and 24.  It turns out that claim adjusters get double credit (in the company&#8217;s idiotic work credit system) for claims with 8 or more parts; triple credit for 16 or more; etc.</p>
<p>The mechanisms by which adjusters can influence the number of parts, to bump 7 up to 8 or 15 up to 16, are weak and subtle &#8212; but they are clearly being leveraged to maximum effect.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: bk</title>
		<link>http://www.johndcook.com/blog/2012/12/24/lucky-house-prices/comment-page-1/#comment-3956</link>
		<dc:creator>bk</dc:creator>
		<pubDate>Mon, 24 Dec 2012 17:27:34 +0000</pubDate>
		<guid isPermaLink="false">http://www.johndcook.com/blog/?p=12670#comment-3956</guid>
		<description><![CDATA[I suspect that Mr Mills is reading from the Trulia real estate blog, which has many more examples and more detail: http://pro.truliablog.com/industry-2/your-homes-lucky-number/]]></description>
		<content:encoded><![CDATA[<p>I suspect that Mr Mills is reading from the Trulia real estate blog, which has many more examples and more detail: <a href="http://pro.truliablog.com/industry-2/your-homes-lucky-number/" rel="nofollow">http://pro.truliablog.com/industry-2/your-homes-lucky-number/</a></p>
]]></content:encoded>
	</item>
</channel>
</rss>
