More Error than Margin

When the newshounds claim something on Fox is ‘false’, that’s a pretty good sign that their margin of error is plus or minus 100%. And yes, that means there’s a catch.
Fox haters of course specialize in lies, but they also excel at rank carelessness enhanced with galloping ignorance. And, in the true fashion of the hater, the more ridiculously erroneous their claims are, the louder they shout them.

So here is the latest example, straight from the venomous mind of Ellen Brodsky herself:
Fox News Poll Falsely Claims Obama's Lead Within The Margin Of Error
Well, that sounds pretty damning. Let’s permit Brodsky to deliver the particulars:
You have to scroll down nine paragraphs to get to this information, obviously spun so as to make the results look as bad as possible for Obama:
Despite voters’ sentiments about their own lives and the economy, 50 percent say President Obama deserves to be re-elected. Almost as many -- 48 percent -- say he doesn’t.
In addition, 45 percent of voters would back Obama and 41 percent Republican Mitt Romney, if the presidential election were held today. Obama’s advantage is within the poll’s three percentage-point margin of sampling error.
It's one thing to spin and another to outright misrepresent your own poll. Last I checked, Obama's 45 percent was four percentage points ahead Romney's 41 percent and, therefore, outside of a three percentage-point margin of error. By the way, I checked to see if the "three" was some kind of typo and it's not.
Ellen Brodsky was so enamored of her 'scoop' that she immediately took to twitter to announce it to all the gullible lemmings who actually believe her drivel:
But Brodsky, who is not a trained media analyst, let alone any sort of statistician, is once again full of it. Let’s look at the link she herself provided, the one that so easily convinced her that Fox is lying. Here it what it shows:
And therein lies the catch. Listen to George Mason University:
The way to understand a poll result such as “49 percent of American voters prefer Bush to Kerry, with a margin of error of three percent” is that 49 percent of those questioned prefer Bush to Kerry. If the poll were conducted again (with a different sample of the population), the percentage of those questioned preferring Bush over Kerry is likely to be a value from 46 (49 minus 3) to 52 (49 plus 3)....If Kerry is leading the polls against Bush by 51 percent to 49 percent, one might think this bodes well for Kerry. However, if there is a three percent margin of error, then there is a substantial chance that the population as a whole supports Kerry as little as 48 percent, and Bush as much as 52 percent.
So an error of plus or minus three points means that each stated result can be either three points higher, or three points lower, than the given numbers. Ergo Obama’s 45% could be 42%, while Romney’s 41% could be as high as 44%.

So Fox (along with the Democratic polling firm that co-wrote the poll results... oops, Brodsky forgot to mention that!) was absolutely correct. The results are within the margin of error. Ellen Brodsky’s screaming headline is wrong. Her claim that this was an attempt to spin is untrue. Her tweet is an unmitigated falsehood. That’s our Sharia Ellen: a triple-threat falsifier.
blog comments powered by Disqus