Monday, October 18, 2004
Galluping error
Why does the Gallup organization even bother?
I continue to read the presidential polls almost every day, but view them pretty much as pseudo- information, like horoscopes. Today's Gallup/CNN/USA Today poll
showing Bush up by 8 points, 52-44, is so unreliable that even CNN reports the supposed 8-point spread as showing "Presidential race is still tight." An 8 point margin is not a tight race, but we all know that the 2004 election is bound to be close. What CNN is telling us between the lines is that they know their own poll numbers are bullshit.
As I pointed out in my September 19 post on presidential polls,
This is half hunch and half wish, but I'd like to see the polling organizations completely blown out of the water this year by a Kerry victory that is so decisive that (a) there is no room for post-election cheating or legal challenges, and (b) the pollsters have to get very reflective about the fact that they missed some major demographic changes that undermine their methods.
I continue to read the presidential polls almost every day, but view them pretty much as pseudo- information, like horoscopes. Today's Gallup/CNN/USA Today poll
showing Bush up by 8 points, 52-44, is so unreliable that even CNN reports the supposed 8-point spread as showing "Presidential race is still tight." An 8 point margin is not a tight race, but we all know that the 2004 election is bound to be close. What CNN is telling us between the lines is that they know their own poll numbers are bullshit.
As I pointed out in my September 19 post on presidential polls,
The Gallup/CNN/USA Today poll on October 10/27/2000, less than a week before the election, reported: Bush 52, Gore 39 !!!Either the Gallup poll uses wildly unreliable methods, or polling is not real information.
This is half hunch and half wish, but I'd like to see the polling organizations completely blown out of the water this year by a Kerry victory that is so decisive that (a) there is no room for post-election cheating or legal challenges, and (b) the pollsters have to get very reflective about the fact that they missed some major demographic changes that undermine their methods.
Subscribe to Posts [Atom]
