Richard Charnin (TruthIsAll)
Sept. 20, 2011
It is instructive to see how the unadjusted 2008 exit polls polls compare to the recorded vote and the True Vote Model (TVM). The basic results are not surprising: Obama did better in the aggregate state exit polls (58.1%) than the vote count (52.9%). But the Democrats always do better in the polls. What is surprising is that he did 5.2% better – exactly matching the TVM. By way of comparison, Kerry did 3.7% better in the unadjusted exit polls (52%) than in the recorded vote (48.3%). He had 53.6% in the TVM.
A Triple Confirmation
In the 2008 National Exit Poll (NEP), 4178 of the 17836 responders were asked how they voted in 2004: 1815 (43.4%) said they were Kerry voters, 1614 (38.6%) Bush, 188 (4.5%) third-party and 561 (13.4%) did not vote. Applying Final 2008 NEP vote shares to the returning voter mix, Obama had a 58.1% share – exactly matching a) his 58.1% share of the aggregate unadjusted state exit polls and b) his 58.1% TVM share! The returning voter mix implied that Kerry won by 50.2-44.6%.
But all exit polls are forced to match the recorded vote. The pollsters needed an impossible 46/37% Bush/Kerry mix which implied that Bush won by 52.6-42.3%. His (bogus) recorded margin was 50.7-48.3%. Kerry won the True Vote with 53.6% (Table 6). In the Final 2008 NEP, pollsters effectively converted 269 of 1815 (15%) Kerry responders to Bush responders in order to force a match to the recorded vote.
To summarize, the unadjusted 2008 NEP exactly matched the weighted aggregate share of the unadjusted state exit polls, based on how the the exit poll responders said they voted in 2004 and 2008. It also matched the TVM which used 2004 votes cast, voter mortality, a best estimate of living 2004 voter turnout in 2008 – and the Final 2008 NEP vote shares. Obama had 58.1% in each calculation – a triple confirmation that Obama won a 23 million vote landslide, far exceeding his 9.5 million recorded vote margin.
But that’s not all. The National Exit Poll of 17836 respondents is a subset of the 80,000 sampled in the state exit polls. Obama won the unadjusted National Exit Poll by 61-37%, a landslide of historic proportions. However, the state exit polls have a smaller margin of error and are probably a better estimate of the True Vote.
This graph shows that Obama’s 58% True Vote share is confirmed by three independent statistical measures: 1) Unadjusted National Exit Poll, 2) Unadjusted state exit polls, 3) and 10 million late (paper ballot) votes.
The key result is the state exit poll aggregate vote share. The national sample size was approximately 80,000. The average state exit poll margin of error was 3.35% (including a 30% “cluster” effect). The margin of error was exceeded in 37 states; in 2004 it was exceeded in 29. Of the 50 states and DC, 45 shifted to McCain from the exit poll. The difference in margin between the exit poll and the recorded vote is the average Within Precinct Discrepancy (WPD). The WPD was 10.6 in 2008, far above the 7.4 in 2004.
The True Vote Model has closely matched the unadjusted state and national exit polls in every presidential election since 1988. In the 11 presidential elections from 1968 to 2008, the Republicans had a 49-45% recorded vote margin while the Democrats had a 49-45% True Vote margin.
In a given state, the exit poll varies from the corresponding True Vote calculation. But the total aggregate share is an exact match, illustrating the Law of Large Numbers and the Central Limit Theorem.
The National True Vote Model is based on previous election votes cast and turnout of previous election voters, current votes cast and National Exit Poll (NEP) vote shares. The State Model works the same way. It’s based on returning state voters with NEP vote shares adjusted according to the state/national vote share ratio.
It should be obvious by now that final weighting adjustments made to the exit polls are made to match the recorded vote. In 2004, in addition to the impossible return voter mix, the 12:22am preliminary national exit poll vote shares had to be adjusted in the Final NEP. The required turnout of living Bush voters was 110%. Kerry had a 52.0% aggregate share and a 53.6% TVM share. Of course, all demographic categories had to be adjusted to match the vote count: Final NEP “Party-ID”, “When Decided” and “Bush Approval” crosstab weights did not match the corresponding pre-election polls and were adjusted to force a match to the recorded vote.