Exit Poll Results Leaked Out, Causing Even More Questions
Remember when I speculated several weeks ago that Mr. Mitofsky’s exit poll may be subject to question when it was found out that he significantly overestimated Bush’s share of the Hispanic vote? As you will recall, the early exit polls done in the early afternoon caused consternation at the White House when they reflected that Kerry was winning by 2-3%. The official line from Rove and later Mitofsky was that these polls had to be wrong because 1) they were premature and had too many Democrats in them; and 2) obviously GOP voters weren’t responding to the exit poll requests as they were leaving the polls. This left us with the conclusion that a flood of GOP voters swept over the polls late on Election Day to deliver the election to Bush, even though to this day there is no evidence of that, or Rove’s claims about the early exit polls.
Well now, it turns out that someone has posted Mitofsky’s PDF exit poll files, which show the first set of exit polls done early Tuesday afternoon on Election Day (which caused the heartburn at the White House), another set of exit polls done as polls were closing on Election Day, and the final exit polls released the next day after Mitofsky weighted them to match the tallied 51%-48% Bush victory.
I haven't had much time to dig into the actual PDFs that were posted, but what I found troubles me so far.
First, in order to get the final 11/3 weighted exit poll to match Bush's final tallied count of a 51%-48% margin, 60% of Mitofsky's sample of 13,660 respondents had to be pulled from the South and Midwest (over 8100 of the 13,660 came from these two regions) while the West and East regions (in other words, Kerrry country) were suppressed in the weighted exit poll that Mitofsky did the day after the election to conform to the tallied results.
Second, if you want to accept the South's regional final (11/3) weighted exit poll results that were used by Mitofsky to construct his final conforming exit poll with a 51%-48% result for Bush, you would also have to accept that the South went 58%-42% for Bush. Yet the exit poll on 11/2 done near poll closing (7:33 PM Eastern) had only a 54%-45% Bush advantage, but it had the same gender breakdown as the 11/3 conforming poll the next day. So in order for Mitofsky to weight the final exit poll to reflect the tallied vote results of a 51%-48% Bush victory, he had to find a way to weight the South with a larger tilt to Bush than it had the day before while keeping the gender breakdown consistent with what it was on 11/2.
And he had to pull 60% of his final exit poll sample from the South and the Midwest in order to make his final national exit poll reflect the tallied results.
I ask you: how plausible is all of this?
I’ll have more on this in the days ahead after more sleep and better informed people weigh in. But feel free to check out the tables yourself, and you will see that in order to get his final exit poll the day after the election to conform to a tallied 51%-48% result for Bush, Mitofsky had to do some real contortions with his poll results, and suppress the vote for Kerry in all regions from what was reported in the last exit poll on Election Day the night before while somehow keeping the gender breakdown the same.