New Study Finds Serious Flaws in UPenn Critic of 04 Bush-Kerry Vote "Shift" Analysis
Remember the exit poll controversy following the 2004 presidential election? It started because of the dramatic change in the election's outlook from the afternoon's exit poll-based assessment that Kerry was winning to President Bush's decisive win once the actual votes were counted. Some on the Left have sought to use that shift to suggest Bush and his top political aide Karl Rove somehow stole the election that Kerry actually won.
Among those fueling such suspicisions has been University of Pennsylvania Professor Steven Freeman, author of a widely quoted paper that argues the shift has not been adequately explained and that vote fraud or mistabulation are the only credible alternative explanations.
Now along comes Stones Cry Out proprietor Rick Brady with a thorough debunking of Freeman's analysis. Here's how Brady summarizes it:
"ABSTRACT: Dr. Steven F. Freeman, visiting University of Pennsylvania (UPenn) professor is not an 'expert' on exit polls or the 2004 Presidential exit poll discrepancies as suggested by this UPenn press release. In fact, his paper, The Unexplained Exit Poll Discrepancy, is highly flawed. His argument that 'in general, exit poll data are sound' fails having suppressed evidence and the conclusion that 'it is impossible that the discrepancies between predicted and actual vote counts in' Ohio, Florida, and Pennsylvania was not substantiated statistically. Nevertheless, Dr. Freeman is right in concluding that explanations of the discrepancy to date are inadequate and Edison/Mitofsky should address the concerns of US Count Votes in subsequent analysis of their data."
Freeman's paper has made possible an urban legend to grow on the Left that has Bush/Rove somehow altering the real vote counts in order to steal the election from Kerry. Brady's work puts that urban legend to rest permanently.