http://www.legjoints.com/AmericanElectionFraud/the-unexplained-exit.pdfThis link was given to me by a new DUer, Roger_Otip. I have downloaded it but it is a pdf file which I can't copy, so I will summarize for you. I would advise all curious about this subject to read it in its entirety though; it is excellent.
"The Unexplained Exit Poll Discrepancy"Steven F. Freeman, PhD
Conclusions: The likelihood that Kerry would receive only 48.5% of the vote in Ohio, with an exit poll of 52.1, is less than 1 in 1,000 (0.0008). The likelihood that Kerry would receive only 47.1% of the vote in Florida, with an exit poll of 49.7, is less than 3 in 1,000 (0.0028). The likelihood that Kerry would receive only 50.8% of the vote in Pennsylvania, with an exit poll of 54.1, is less than 2 in 1,000 (0.0018)."The likelihood of any two of these three statistical anomalies occurring together is on the order of 1 in 1 million. The odds against all three occurring together are 250 million to one. As much as we can say in social science that something is impossible, it is impossible that the discrepancies between predicted and actual vote counts in the three critical battleground states of the 2004 election could have been due to chance or random error."Dr. Freeman is on faculty at the University of Pennsylvania, and received his PhD from MIT. He uses the exit poll data from Jonathon Simon, who has posted his analysis at DU. (I'll get back with the thread.) He discusses the problems of unpublished exit poll data from Edison and Mitofsky, and debunks some of the circulating myths about the invalidity of exit poll data in this election.