<?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: Fox News mangles stats, denies error</title>
	<atom:link href="http://www.lancebledsoe.com/fox-news-mangles-stats-denies-error/feed/" rel="self" type="application/rss+xml" />
	<link>http://www.lancebledsoe.com/fox-news-mangles-stats-denies-error/</link>
	<description>Data junkie. Math geek. Rock star.</description>
	<lastBuildDate>Wed, 08 Sep 2010 18:05:48 +0000</lastBuildDate>
	<sy:updatePeriod>hourly</sy:updatePeriod>
	<sy:updateFrequency>1</sy:updateFrequency>
	<generator>http://wordpress.org/?v=3.0</generator>
	<item>
		<title>By: bledsoe</title>
		<link>http://www.lancebledsoe.com/fox-news-mangles-stats-denies-error/comment-page-1/#comment-1229</link>
		<dc:creator>bledsoe</dc:creator>
		<pubDate>Fri, 08 Jan 2010 10:59:06 +0000</pubDate>
		<guid isPermaLink="false">http://www.lancebledsoe.com/?p=1090#comment-1229</guid>
		<description>First of all, I did provide in my post both of the links you reference.  Your first link (Rasmussen&#039;s summary of their poll results) I provided in my third numbered point hyperlinked to the phrase &quot;summary of the results.&quot;  Your second link (the survey questions and results) I provided in my second numbered point hyperlinked to the phrase &quot;national survey.&quot;

Second, we both agree that Rasmussen reported their poll results accurately.  In their summary of the results, Rasmussen combined the 35% Very Likely category and the 24% Somewhat Likely category and summarized them as a single &quot;at least somewhat likely&quot; category of 59%.  This is completely accurate, and is not misleading in any way.  As I noted in my post, this combining of survey response categories is done all the time when summarizing survey data.

However, to claim that Fox &quot;[accurately] reported what Rasmussen said&quot; is simply not true, and it&#039;s the Fox-created graphic which inaccurately reports the Rasmussen data.  Specifically, the 59% category in the graphic should have been labeled &quot;At least somewhat likely&quot; (or something similar), since that&#039;s what the 59% category represents; it does not represent Somewhat Likely, as stated on the graphic.  The 35% Very Likely category should have then been left off the graphic completely, since those Very Likely responses had already been reported on the graphic under the 59% category; to display them again in a separate category implies that the Very Likely responses are a different set of responses from the &quot;At least somewhat likely&quot; responses, which is false and misleading.  (An indication of just how misleading the graphic was, is the fact that the Fox commentators themselves misunderstood the information which the graphic was attempting to provide.)

Even better would have been for Fox to display a graphic showing all five of the response categories for that question, along with the associated percentages, and not combined the percentages at all in the graphic.  Then, if they wanted to make the point that 59% of survey respondents &quot;said it was at least somewhat likely that some scientists had falsified research...&quot; they could make that point in their verbal commentary.  This is essentially what Rasmussen did with their separate &quot;survey results&quot; and &quot;survey summary&quot; reports, and is again standard procedure when reporting survey results.

The bottom line is that one of the basic responsibilities of a news organization is to report information in a manner that helps the viewer to accurately understand and make sense of the issue, and one can&#039;t do that if the graphics one uses are confusing and misleading.

Again, I&#039;m not claiming that Fox&#039;s mistake was a hanging offense.  Sometimes people make mistakes and this was an easy one to make.  But when the mistake was pointed out (by several people), Fox should have acknowledged it rather than denying it.</description>
		<content:encoded><![CDATA[<p>First of all, I did provide in my post both of the links you reference.  Your first link (Rasmussen's summary of their poll results) I provided in my third numbered point hyperlinked to the phrase "summary of the results."  Your second link (the survey questions and results) I provided in my second numbered point hyperlinked to the phrase "national survey."</p>
<p>Second, we both agree that Rasmussen reported their poll results accurately.  In their summary of the results, Rasmussen combined the 35% Very Likely category and the 24% Somewhat Likely category and summarized them as a single "at least somewhat likely" category of 59%.  This is completely accurate, and is not misleading in any way.  As I noted in my post, this combining of survey response categories is done all the time when summarizing survey data.</p>
<p>However, to claim that Fox "[accurately] reported what Rasmussen said" is simply not true, and it's the Fox-created graphic which inaccurately reports the Rasmussen data.  Specifically, the 59% category in the graphic should have been labeled "At least somewhat likely" (or something similar), since that's what the 59% category represents; it does not represent Somewhat Likely, as stated on the graphic.  The 35% Very Likely category should have then been left off the graphic completely, since those Very Likely responses had already been reported on the graphic under the 59% category; to display them again in a separate category implies that the Very Likely responses are a different set of responses from the "At least somewhat likely" responses, which is false and misleading.  (An indication of just how misleading the graphic was, is the fact that the Fox commentators themselves misunderstood the information which the graphic was attempting to provide.)</p>
<p>Even better would have been for Fox to display a graphic showing all five of the response categories for that question, along with the associated percentages, and not combined the percentages at all in the graphic.  Then, if they wanted to make the point that 59% of survey respondents "said it was at least somewhat likely that some scientists had falsified research..." they could make that point in their verbal commentary.  This is essentially what Rasmussen did with their separate "survey results" and "survey summary" reports, and is again standard procedure when reporting survey results.</p>
<p>The bottom line is that one of the basic responsibilities of a news organization is to report information in a manner that helps the viewer to accurately understand and make sense of the issue, and one can't do that if the graphics one uses are confusing and misleading.</p>
<p>Again, I'm not claiming that Fox's mistake was a hanging offense.  Sometimes people make mistakes and this was an easy one to make.  But when the mistake was pointed out (by several people), Fox should have acknowledged it rather than denying it.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Father</title>
		<link>http://www.lancebledsoe.com/fox-news-mangles-stats-denies-error/comment-page-1/#comment-1220</link>
		<dc:creator>Father</dc:creator>
		<pubDate>Wed, 06 Jan 2010 16:13:22 +0000</pubDate>
		<guid isPermaLink="false">http://www.lancebledsoe.com/?p=1090#comment-1220</guid>
		<description>Yea, so a link to the actual poll would have been nice for you to provide:

http://www.rasmussenreports.com/public_content/politics/current_events/environment_energy/americans_skeptical_of_science_behind_global_warming

and something that you and the liberal group Media Matters don&#039;t mention:
Fox reported it exactly as Rasmussen polled it.

&quot;Fifty-nine percent (59%) of Americans say it’s at least somewhat likely that some scientists have falsified research data to support their own theories and beliefs about global warming. Thirty-five percent (35%) say it’s Very Likely. Just 26% say it’s not very or not at all likely that some scientists falsified data.&quot;

the questions Rasmussen asked are listed here:
http://www.rasmussenreports.com/public_content/business/econ_survey_toplines/december_2009/toplines_climate_change_december_1_2_2009

Specifically Question #3:
3* In order to support their own theories and beliefs about global warming, how likely is it that some scientists have falsified research data?
35% Very likely
24% Somewhat likely
21% Not very likely
5% Not at all likely
15% Not sure

So, as Rasmussen stated in their summary:

&quot;Fifty-nine percent (59%) of Americans say it’s at least somewhat likely that some scientists have falsified research data to support their own theories and beliefs about global warming.&quot; (Notice the end of the sentence, as signaled by that little dot)

This is accurate. as 35% said &quot;Very likely&quot; and 24% said &quot;Somewhat likely&quot;

Then Rasmussen said:
&quot;Thirty-five percent (35%) say it’s Very likely. Just 26% say it’s not very or not at all likely that some scientists falsified data.&quot;

This too is accurate, as per their poll.

Fox reported what Rasmussen said.  It is unfortunate for those who are not smart enough to look up the information, and jump to whatever conclusions they want, but the Church of Global Warming here is simply seeing what they want.  But the bottom line of it is:  Fox News was indeed correct in their reporting, though many were incorrect in their interpretation of Fox’s reporting.</description>
		<content:encoded><![CDATA[<p>Yea, so a link to the actual poll would have been nice for you to provide:</p>
<p><a href="http://www.rasmussenreports.com/public_content/politics/current_events/environment_energy/americans_skeptical_of_science_behind_global_warming" rel="nofollow">http://www.rasmussenreports.com/public_content/politics/current_events/environment_energy/americans_skeptical_of_science_behind_global_warming</a></p>
<p>and something that you and the liberal group Media Matters don't mention:<br />
Fox reported it exactly as Rasmussen polled it.</p>
<p>"Fifty-nine percent (59%) of Americans say it’s at least somewhat likely that some scientists have falsified research data to support their own theories and beliefs about global warming. Thirty-five percent (35%) say it’s Very Likely. Just 26% say it’s not very or not at all likely that some scientists falsified data."</p>
<p>the questions Rasmussen asked are listed here:<br />
<a href="http://www.rasmussenreports.com/public_content/business/econ_survey_toplines/december_2009/toplines_climate_change_december_1_2_2009" rel="nofollow">http://www.rasmussenreports.com/public_content/business/econ_survey_toplines/december_2009/toplines_climate_change_december_1_2_2009</a></p>
<p>Specifically Question #3:<br />
3* In order to support their own theories and beliefs about global warming, how likely is it that some scientists have falsified research data?<br />
35% Very likely<br />
24% Somewhat likely<br />
21% Not very likely<br />
5% Not at all likely<br />
15% Not sure</p>
<p>So, as Rasmussen stated in their summary:</p>
<p>"Fifty-nine percent (59%) of Americans say it’s at least somewhat likely that some scientists have falsified research data to support their own theories and beliefs about global warming." (Notice the end of the sentence, as signaled by that little dot)</p>
<p>This is accurate. as 35% said "Very likely" and 24% said "Somewhat likely"</p>
<p>Then Rasmussen said:<br />
"Thirty-five percent (35%) say it’s Very likely. Just 26% say it’s not very or not at all likely that some scientists falsified data."</p>
<p>This too is accurate, as per their poll.</p>
<p>Fox reported what Rasmussen said.  It is unfortunate for those who are not smart enough to look up the information, and jump to whatever conclusions they want, but the Church of Global Warming here is simply seeing what they want.  But the bottom line of it is:  Fox News was indeed correct in their reporting, though many were incorrect in their interpretation of Fox’s reporting.</p>
]]></content:encoded>
	</item>
</channel>
</rss>
