<?xml version="1.0" encoding="UTF-8"?>
<rss version="2.0"
	xmlns:content="http://purl.org/rss/1.0/modules/content/"
	xmlns:wfw="http://wellformedweb.org/CommentAPI/"
	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/"
	xmlns:slash="http://purl.org/rss/1.0/modules/slash/"
	>

<channel>
	<title>Metrics Geek &#187; When Good Measurement Goes Bad</title>
	<atom:link href="http://metricsgeek.com/category/when-good-measurement-goes-bad/feed/" rel="self" type="application/rss+xml" />
	<link>http://metricsgeek.com</link>
	<description>Because Everything is Measurable</description>
	<lastBuildDate>Fri, 06 Jan 2012 14:39:07 +0000</lastBuildDate>
	<language>en</language>
	<sy:updatePeriod>hourly</sy:updatePeriod>
	<sy:updateFrequency>1</sy:updateFrequency>
	<generator>http://wordpress.org/?v=3.3.2</generator>
		<item>
		<title>Mercator Projection</title>
		<link>http://metricsgeek.com/2010/03/mercator-projection/</link>
		<comments>http://metricsgeek.com/2010/03/mercator-projection/#comments</comments>
		<pubDate>Tue, 23 Mar 2010 19:17:06 +0000</pubDate>
		<dc:creator>Geek</dc:creator>
				<category><![CDATA[When Good Measurement Goes Bad]]></category>

		<guid isPermaLink="false">http://metricsgeek.com/?p=130</guid>
		<description><![CDATA[I used to have a professor who ranted (seemingly at random moments in a lecture) that &#8220;the map is NOT the territory, people!&#8221; At the time I didn&#8217;t care too much what the heck he meant because those inane ramblings never showed up on final exams. Many years later however, I find that this is [...]]]></description>
			<content:encoded><![CDATA[<p>I used to have a professor who ranted (seemingly at random moments in a lecture) that &#8220;the map is NOT the territory, people!&#8221;</p>
<p>At the time I didn&#8217;t care too much what the heck he meant because those inane ramblings never showed up on final exams. Many years later however, I find that this is some of the most useful information I got from my undergraduate time spent. The gist of the message (as I&#8217;m interpreting it now) is that the effort of creating a representation of a real-life situation will always result in bias.</p>
<p>This is why there has been so much research into the <a href="http://www.apa.org/monitor/apr06/eyewitness.aspx">validity of eye-witness testimony</a>&#8230;because while it seem simple that someone on the scene should be able to relay what they saw and what they heard in order to provide an objective account; the truth is that eye-witness testimony is often unreliable.</p>
<p>So today&#8217;s lesson is about the subjectivity of reality based on how it&#8217;s measured! (yay for subjectivity!)</p>
<p>&#8220;The map is not the territory&#8221; is nowhere more clear than in how maps are made. Way back in the 1500&#8242;s Flemish geographer <a href="http://en.wikipedia.org/wiki/Mercator_projection">Gerardus Mercator</a> came up with the most commonly-used method for displaying a sphere (the earth) in two dimensions (on a map). The problem is that most of us (certainly I) grew up believing that the map represented what was true about the earth! Here are some differences:</p>
<ul>
<li>Greenland is presented as having roughly as much land area as Africa,  when in fact Africa&#8217;s area is approximately 14 times greater than  Greenland.</li>
<li>Alaska is presented as having similar or even slightly more land area than Brazil,  when Brazil&#8217;s area is actually more than 5 times that of Alaska.</li>
<li>Finland appears with a greater north-south extent than India,  although India&#8217;s is the greater.</li>
</ul>
<p>Additionally, the maps I grew up looking at (and still look at) show north at the top. North, of course, is an arbitrary direction associated with one of the two points of the axis on which the earth turns. There is, of course, no &#8220;up&#8221; in space&#8230;so representing north at the top of a map is completely arbitrary. Or, as is more likely, completely self-centered. It is SO not coincidental that most maps that school children see in America have the United States at the top center.</p>
<p>My strong recommendation is that you all go <a href="http://www.maps.com/map.aspx?cid=22,57,99&amp;pid=17276&amp;nav=MS">online </a>and order yourself a map with Australia at the top center. Spend some time studying the map. What do you notice that maybe you haven&#8217;t noticed before? Personally I don&#8217;t think I had ever noticed the Kamchatka Peninsula before but on my revised Australia-centric map, it stands out quite prominently.</p>
<p>The point here is that the choice we make to display or represent a situation will include bias whether we want it to or not. Next time you look at a map or a bar chart or a flow chart or ANY graphic representation&#8230;what questions will you ask that help you understand the bias?</p>
<p>~Geek~</p>
]]></content:encoded>
			<wfw:commentRss>http://metricsgeek.com/2010/03/mercator-projection/feed/</wfw:commentRss>
		<slash:comments>0</slash:comments>
		</item>
		<item>
		<title>Incenting Weight Loss</title>
		<link>http://metricsgeek.com/2010/02/incenting-weight-loss/</link>
		<comments>http://metricsgeek.com/2010/02/incenting-weight-loss/#comments</comments>
		<pubDate>Mon, 01 Feb 2010 16:37:17 +0000</pubDate>
		<dc:creator>Geek</dc:creator>
				<category><![CDATA[When Good Measurement Goes Bad]]></category>

		<guid isPermaLink="false">http://metricsgeek.com/?p=121</guid>
		<description><![CDATA[In the continuing category of When Good Measurement Goes Bad, today&#8217;s question is about Whole Foods. These nice folks, who are (in my humble opinion) the quintessential yuppie expression of enlightenment, have recently decided employees can get an even better employee discount if they are healthier, specifically if they have lower cholesterol, don&#8217;t smoke and [...]]]></description>
			<content:encoded><![CDATA[<p>In the continuing category of When Good Measurement Goes Bad, today&#8217;s question is about <a href="http://www.wholefoodsmarket.com/">Whole Foods</a>. These nice folks, who are (in my humble opinion) the quintessential yuppie expression of enlightenment, have <a href="http://www.nydailynews.com/lifestyle/health/2010/01/26/2010-01-26_whole_foods_to_give_greater_employee_discounts_to_workers_with_lower_bmi_cholest.html">recently decided</a> employees can get an even better employee discount if they are healthier, specifically if they have lower cholesterol, don&#8217;t smoke and have a lower BMI.</p>
<p>My hope and expectation is that someone at Whole Foods who is paid to analyze finances, as opposed to being paid to select local organic oranges, ran the numbers on increasing health insurance costs for the coverage provided to employees and determined that these deeper discounts were worth it if they could inspire a healthier workforce and lower some of those costs.</p>
<p>So here&#8217;s the rub. It seems sort of uncomfortably oligarchy-ish for Corporate America to incent good behavior this way. Whole Foods is not the boss of their employees&#8217; bodies, darnit!</p>
<p>But didn&#8217;t Corporate America kind of already incent us to develop the crappy eating habits that led to all this food-related unhealthiness? Diabetes and obesity and the myriad other maladies that go along with poor eating habits? Didn&#8217;t Corporate America, in order to line its already plush pockets, create fast food drive-&#8221;thrus&#8221;, high fructose corn syrup and  <a href="http://brands.kraftfoods.com/lunchables/">Lunchables</a>, and haven&#8217;t all of those things already screwed up our quality of life?</p>
<p>I think I&#8217;m OK with this. I think I&#8217;m OK with Corporate America (in this case, Whole Foods) responding to the only thing that matters to them&#8230;how to make more money or spend less money. In this case, if their desire to reduce costs leads them to reward healthy behavior in their employees, I&#8217;m all for it.</p>
<p>Go forth and measure&#8230;</p>
<p>~Geek~</p>
]]></content:encoded>
			<wfw:commentRss>http://metricsgeek.com/2010/02/incenting-weight-loss/feed/</wfw:commentRss>
		<slash:comments>0</slash:comments>
		</item>
		<item>
		<title>Decimate the competition</title>
		<link>http://metricsgeek.com/2009/10/decimate-the-competition/</link>
		<comments>http://metricsgeek.com/2009/10/decimate-the-competition/#comments</comments>
		<pubDate>Thu, 15 Oct 2009 17:20:56 +0000</pubDate>
		<dc:creator>Geek</dc:creator>
				<category><![CDATA[When Good Measurement Goes Bad]]></category>

		<guid isPermaLink="false">http://metricsgeek.com/?p=94</guid>
		<description><![CDATA[Where measurement and etymology meet. Getting some refresher info on mutually exclusive random sampling, I came across a definition of &#8220;decimate&#8221;. Decimation (Latin: decimatio; decem = &#8220;ten&#8221;) was a form of military discipline used by officers in the Roman Army to punish mutinous or cowardly soldiers. The word decimation is derived from Latin meaning &#8220;removal [...]]]></description>
			<content:encoded><![CDATA[<p>Where measurement and etymology meet. Getting some refresher info on mutually exclusive random sampling, I came across a definition of &#8220;decimate&#8221;.</p>
<p style="padding-left: 30px;"><a href="http://en.wikipedia.org/wiki/Decimation_(Roman_army)">Decimation </a>(Latin: decimatio; decem = &#8220;ten&#8221;) was a form of military discipline used by officers in the Roman Army to punish mutinous or cowardly soldiers. The word decimation is derived from Latin meaning &#8220;removal of a tenth.</p>
<p>OMG, really? I see the connection now&#8230;&#8221;dec&#8221;, like &#8220;decimal&#8221; in a base-ten system.</p>
<p>So apparently (according to Wikipedia), a form of punishment for Roman Soldiers was to decimate them&#8230;to literally choose one soldier in 10 by lottery and have the other nine soldiers kill that one by stoning or clubbing (and not the kind of clubbing practiced in trendy downtown neighborhoods by festive hipsters, either).</p>
<p>The most interesting thing here (to me) is that some professor, whose statistics class notes are randomly available online, felt compelled to explain this little tidbit of trivia as an example of appropriate random population sampling. Dark, yes?</p>
<p>Bring this up in conversation today, I dare you.</p>
<p>~Geek~</p>
<p><em><br />
</em></p>
]]></content:encoded>
			<wfw:commentRss>http://metricsgeek.com/2009/10/decimate-the-competition/feed/</wfw:commentRss>
		<slash:comments>0</slash:comments>
		</item>
	</channel>
</rss>

