A Database and True Vote Model for Analyzing 1988-2008 State Exit Poll Discrepancies
Updated: April 10, 2012
Unadjusted exit polls are based on actual respondent totals. Final Exit Polls are always forced to match the recorded vote. The unadjusted exit polls are confirmed in other surveys and the True Vote Model.
This workbook includes 1988-2008 unadjusted “pristine” state exit poll data and reflects actual voter response.
This graph summarizes the discrepancies between the1988-2008 State Exit Polls vs. the corresponding Recorded Votes
The True Vote Model
The TVM is based on Census votes cast, mortality, prior election voter turnout and National Exit Poll vote shares. The TVM closely matched the unadjusted exit polls in each election from 1988-2008.
The 1988-2008 State and National True Vote Model
Roper Center: The Data Source
In the 1988-2008 presidential elections, the exit poll margin of error was exceeded in 126 of 274 state exit polls, with 123 shifting in favor of the Republicans and just 3 for the Democrats. At the 95% confidence level, one would expect that the margin of error would be exceeded in 7-8 states in favor of the GOP and 7-8 for the Democrat. The probability that the margin of error would be exceeded in a state election is 5% (2.5% for the Democrat and 2.5% for the Republican).
The Probability P that 123 of 274 exit polls would shift to the GOP beyond the margin of error) is calculated as:
P = 5.4E-106 = Poisson (123,.025*274, false) or
1 in 1.8 BILLION TRILLION TRILLION TRILLION TRILLION TRILLION TRILLION TRILLION TRILLION!
Therefore it is proof beyond ANY DOUBT that election fraud is systemic and virtually always favors the GOP. Based on the UNADJUSTED exit polls, the Democrats should have won ALL SIX elections.
From the Intro worksheet:
The Democrats led in all the 1988-2008 presidential election averages…
1) recorded vote: 47.9 – 45.9%
2) unadjusted state exit poll aggregate: 51.8 – 41.6%; unadjusted national exit poll: 51.7- 41.7%
3) True Vote Model (methods 2-3): 51.6 – 42.9%
4) True Vote Model (method 4): 53.0 – 41.0%
5) Exit Poll (WPE/IMS method): 50.8 – 43.1%
These states flipped to the GOP from the exit poll to the recorded vote:
1988: CA CO IL LA MD MI MT NM PA SD VT
Dukakis had a 51-47% edge in 24 battleground state polls.
He lost by 7 million votes.
1992: AK AL AZ FL IN MS NC OK TX VA
Clnton had a 18 million vote margin in the state exit polls.
He won the recorded vote by just 6 million.
1996: AK AL CO GA ID IN MS MT NC ND SC SD VA
Clinton had a 16 million vote margin in the state exit polls.
He won by just 8 million recorded votes.
2000: AL AR AZ CO FL GA MO NC NV TN TX VA
Gore needed just ONE of these states to win the election.
He won the state exit polls by 6 million, matching the TVM.
2004: CO FL IA MO NM NV OH VA
Kerry needed FL or OH to win.
He won the national and state exit polls by 5-6 million with 51-52%.
He won the TVM by 10 million with 53.6%.
2008: AL AK AZ GA MO MT NE
Obama had 58% in the state exit polls, a 23 million margin (9.5 recorded).
He had 61% in the unadjusted National Exit Poll.
The True Vote Model indicated that he had 58.0% exactly matching the unadjusted state exit polls.
To force State and National Exit Polls to match the recorded vote, all demographic category weights and/or vote shares have to be adjusted.
Bush Approval Ratings
For example, to adjust Kerry’s 51.1 – 47.5% unadjusted exit poll margin to Bush’s 50.7- 48.3% recorded margin in the Final National Exit Poll.
Bush’s 50.3% unadjusted approval rating was increased to 53%.
Corresponding vote shares were increased as well.
Bush had just 48% approval in the final pre-election polls.
With 48% approval applied to the NEP shares, Kerry had 53.7% (see the sensitivity analysis table below).
Dem/Rep Party-ID was changed from 38.5-35.1% to 37-37% to match the vote.
There was a near-perfect correlation between Bush’s unadjusted state exit poll shares, approval ratings and Party-ID.
US Count Votes analysis of the Ohio 2004 exit poll discrepancies:
UCSV proved the impossibility of the exit pollster’s reluctant Bush responder (rBr) hypothesis. The rBr theory was promoted to explain the cause of the 6.5% exit poll discrepancies. It stated that 56 Kerry voters responded to be interviewed for every 50 Bush voters.
The Exit Poll Response Optimizer confirmed the USCV simulation.