<?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: Statistics as journalism redux: Benford&#8217;s Law used to question company accounts</title>
	<atom:link href="http://onlinejournalismblog.com/2011/10/13/statistics-as-journalism-redux-benfords-law-used-to-question-company-accounts/feed/" rel="self" type="application/rss+xml" />
	<link>http://onlinejournalismblog.com/2011/10/13/statistics-as-journalism-redux-benfords-law-used-to-question-company-accounts/</link>
	<description>A conversation.</description>
	<lastBuildDate>Mon, 21 May 2012 12:30:09 +0000</lastBuildDate>
	<sy:updatePeriod>hourly</sy:updatePeriod>
	<sy:updateFrequency>1</sy:updateFrequency>
	<generator>http://wordpress.org/?v=3.3.2</generator>
	<item>
		<title>By: When data goes bad &#124; Online Journalism Blog</title>
		<link>http://onlinejournalismblog.com/2011/10/13/statistics-as-journalism-redux-benfords-law-used-to-question-company-accounts/#comment-370305</link>
		<dc:creator>When data goes bad &#124; Online Journalism Blog</dc:creator>
		<pubDate>Thu, 19 Apr 2012 13:36:20 +0000</pubDate>
		<guid isPermaLink="false">http://onlinejournalismblog.com/?p=15227#comment-370305</guid>
		<description>[...] Diego also used the Benford&#8217;s Law technique to identify potentially fraudulent data, which was also used to highlight relationships between dodgy company data and real world events such as the dotcom .... [...]</description>
		<content:encoded><![CDATA[<p>[...] Diego also used the Benford&#8217;s Law technique to identify potentially fraudulent data, which was also used to highlight relationships between dodgy company data and real world events such as the dotcom &#8230;. [...]</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: A magical fraud finder &#171; magic dashboards</title>
		<link>http://onlinejournalismblog.com/2011/10/13/statistics-as-journalism-redux-benfords-law-used-to-question-company-accounts/#comment-174444</link>
		<dc:creator>A magical fraud finder &#171; magic dashboards</dc:creator>
		<pubDate>Sat, 29 Oct 2011 13:15:06 +0000</pubDate>
		<guid isPermaLink="false">http://onlinejournalismblog.com/?p=15227#comment-174444</guid>
		<description>[...] Here is a great article explaining some real world uses, from spotting financial fraud to spotting fiddled murder statistics. [...]</description>
		<content:encoded><![CDATA[<p>[...] Here is a great article explaining some real world uses, from spotting financial fraud to spotting fiddled murder statistics. [...]</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Paul Bradshaw</title>
		<link>http://onlinejournalismblog.com/2011/10/13/statistics-as-journalism-redux-benfords-law-used-to-question-company-accounts/#comment-159537</link>
		<dc:creator>Paul Bradshaw</dc:creator>
		<pubDate>Thu, 13 Oct 2011 14:53:46 +0000</pubDate>
		<guid isPermaLink="false">http://onlinejournalismblog.com/?p=15227#comment-159537</guid>
		<description>Thanks Tony - both comments very helpful. Also spotted your tweet about the idea of a Google Refine functionality to do this. There are plugins for Refine so someone could write one...</description>
		<content:encoded><![CDATA[<p>Thanks Tony &#8211; both comments very helpful. Also spotted your tweet about the idea of a Google Refine functionality to do this. There are plugins for Refine so someone could write one&#8230;</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Tony Hirst</title>
		<link>http://onlinejournalismblog.com/2011/10/13/statistics-as-journalism-redux-benfords-law-used-to-question-company-accounts/#comment-159333</link>
		<dc:creator>Tony Hirst</dc:creator>
		<pubDate>Thu, 13 Oct 2011 10:50:26 +0000</pubDate>
		<guid isPermaLink="false">http://onlinejournalismblog.com/?p=15227#comment-159333</guid>
		<description>PS to previous comment - the actual use case I linked to is *not* a good example when it comes to actually checking data against Benford&#039;s Law. Benford&#039;s Law applies when the data spans several orders of magnitude (tens, hundreds, thousands, tens of thousands, etc) not, as in the example i linked to, a single decade. The test probably be more appropriate when applied to eg leading digits in local council expenses, where invoices ranging from 10s of pounds to millions of pounds might be expected.</description>
		<content:encoded><![CDATA[<p>PS to previous comment &#8211; the actual use case I linked to is *not* a good example when it comes to actually checking data against Benford&#8217;s Law. Benford&#8217;s Law applies when the data spans several orders of magnitude (tens, hundreds, thousands, tens of thousands, etc) not, as in the example i linked to, a single decade. The test probably be more appropriate when applied to eg leading digits in local council expenses, where invoices ranging from 10s of pounds to millions of pounds might be expected.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Tony Hirst</title>
		<link>http://onlinejournalismblog.com/2011/10/13/statistics-as-journalism-redux-benfords-law-used-to-question-company-accounts/#comment-159292</link>
		<dc:creator>Tony Hirst</dc:creator>
		<pubDate>Thu, 13 Oct 2011 10:15:41 +0000</pubDate>
		<guid isPermaLink="false">http://onlinejournalismblog.com/?p=15227#comment-159292</guid>
		<description>So having identified Benford&#039;s Law as an analytical technique that we can use as a way of gaining confidence, or not, in a dataset, the next question is: how do I apply it?

This post - http://www.decisionsciencenews.com/2011/10/05/do-cents-follow-benfords-law/ - includes a couple of methods (one using R, one using a Unix command-line tool), which can maybe represent a starting point for bootstrapping up from &#039;some programming required&quot; to &#039;click here to run Benford&#039;s law test&#039;?</description>
		<content:encoded><![CDATA[<p>So having identified Benford&#8217;s Law as an analytical technique that we can use as a way of gaining confidence, or not, in a dataset, the next question is: how do I apply it?</p>
<p>This post &#8211; <a href="http://www.decisionsciencenews.com/2011/10/05/do-cents-follow-benfords-law/" rel="nofollow" onclick="urchinTracker('/outgoing/www.decisionsciencenews.com/2011/10/05/do-cents-follow-benfords-law/?referer=');">http://www.decisionsciencenews.com/2011/10/05/do-cents-follow-benfords-law/</a> &#8211; includes a couple of methods (one using R, one using a Unix command-line tool), which can maybe represent a starting point for bootstrapping up from &#8216;some programming required&#8221; to &#8216;click here to run Benford&#8217;s law test&#8217;?</p>
]]></content:encoded>
	</item>
</channel>
</rss>

