Thursday, September 18, 2008

It's Not A Statistical Dead Heat!

Ok, this is mostly a personal gripe of mine, and it's neither pro-Obama or pro-McCain. It's anti-person on teevee telling me that a race is a statistical dead heat because a poll is within the margin of error. That's not what the margin of error means!!!!!!!

!!!

(Seriously, it pisses me off)

And now some background on the margin of error.

Those who conduct a poll require a specific level of confidence. And they set the level of confidence, typically to 95% (or 90%). When the level of confidence is 95%, it means if you asked 1000 different people 1000 times (or whatever), 95% of these samples would fall within the margin of error, in this case 3 %.
And just in case Salon isn't convincing for you, here's the National Council on Public Polls.
Certainly, if the gap between the two candidates is less than the sampling error margin, you should not say that one candidate is ahead of the other. You can say the race is "close," the race is "roughly even," or there is "little difference between the candidates." But it should not be called a "dead heat" unless the candidates are tied with the same percentages. And it certainly is not a “statistical tie” unless both candidates have the same exact percentages.
So the bottom line is if the poll has a margin of error of say 4, you and someone has a lead of +1, then you can be pretty sure that they're actually somewhere between -3 and +5, but saying it's tied is about the same as saying it's -3 because really we just don't know.

So could everyone stop saying 'statistical tie' or 'dead heat' and lets just say that the election, as it stands now, is pretty damn close.

2 comments:

  1. I was not aware of that. However, I'm not surprised the media is not good at statistics. Thanks.

    ReplyDelete
  2. Good job explain confidence levels and margin of error! Nice! You can come teach that to my stat students now! (And I agree, the media SUCKS at interpreting polls.)

    ReplyDelete