Nov. 14, 2009
The 2008 election was a virtual duplicate of the 2006 midterms. The unadjusted and final exit polls both showed a 9% discrepancy in margin.
In 2006, a 120-Generic Poll trend model projected that the
Democrats would win 56.43% (assuming they captured 60% of the undecided vote).
The unadjusted 2006 National Exit Poll indicated that they had 56.37%; the 7pm
adjusted NEP had 55.3%. The Final NEP was forced to match the recorded 52.2%
share. The Democratic margin was
reduced from 15.1% to 6.3%. The pre-election Generic 120 poll trend
matched the exit poll to within .07%!
The Final 2008 NEP indicates that Obama's true margin was
also cut from 16.1% to 7.3%. As usual, the Final was forced to match the
recorded vote and revealed once again that the recorded vote was bogus, just
like it was in 2006 and 2004. Obama won
the official, recorded vote by 52.9-45.6%. The Election Calculator model
indicates that he won by 55.4-43.0%, assuming that Bush won a fraud-free
election in 2004 by 50.7-48.3%. Obama won by 57.2-41.1% assuming that
2004 was stolen and Kerry won by 52-47%.
The 2008 unadjusted state exit polls have not been released. Exit pollsters Edison-Mitofsky provided 2004 data on Jan. 19, 2005 - one day before the second Bush inaugural. The unadjusted 2008 state exit poll data would show that Obama won by at least double his 9.5m vote recorded margin. But will the mainstream media (that sponsored the poll) release it?
Are you listening, Keith and Rachel?
In 2006, 120 Pre-election House Generic Polls asked the question: Which congressional candidate are you going to vote for, the Democrat or Republican?
I created a trend line model based on a simple linear ("best-fit") regression of the 120 poll shares. The model projected the Democrats would win 56.43% of the House Generic vote.
The Linear Regression Trend Model produced the following "best fit" trend lines.
Dem = 46.98 + .0419x
Rep = 38.06 + .0047x
Substituting x = 120 and allocating 60% of undecided voters (UVA) to the Democrats:
Dem = 52.01
+ 4.42 = 56.43%
Rep = 38.62
+ 2.95 = 41.57%
http://img.photobucket.com/albums/v474/autorank/Election2006_16921_image001.png
Exit pollsters Edison-Mitofsky asked 13,251 responders:
Who did you just vote for, the Democrat or Republican?
The 13251 respondents indicated that the Democrats won the poll by 56.37- 41.33%.
A little more than half (6351) were asked who they voted for in 2004.
http://www.ropercenter.uconn.edu/elections/common/exitpolls.html
If we assume the unadjusted exit poll mix of returning Kerry and Bush voters and adjust vote shares to match the unadjusted exit poll:
The Final NEP was forced to match the 52.2-45.9% recorded margin by
1) adjusting the returning Kerry/Bush voter mix to an implausible 43/49%
2) lowering the Democratic shares of returning Kerry and Bush voters by approximately 2-3%.
In order to match the 56.37-41.33% vote split using 7pm NEP vote shares, the returning voter mix had to be revised:
1) the impossible 4.0% Other mix was lowered to 1.0% to match the 2004 recorded share.
2) the Kerry/Bush returning voter mix was changed to 48.5/46.5%.
Bush vote shares had to be lowered to match the unadjusted exit poll. The Final NEP radically changed the 7pm MIX and shares in order match the recorded vote.
Note that the 7pm returning voter mix was dubious since it assumed that the recorded 2004 vote was the True Vote.
Comparison Summary 2006/2008
2006
Model 56.43
(Pre-election Generic 120 Poll trend line model)
Unadj 56.37%
(“pristine”, plausible 46.5/48.5 Bush/Gore mix)
7pm 55.20
(implausible 47/45 mix)
Final 52.19
(forced to match recorded vote, 49/43 mix)
2008
Final
52.62% (forced to match)
Recorded
52.87
Scenario 1 55.38%
(assumes returning voter mix based on fraud-free 2004 recorded vote
(Bush 50.7-48.3%)
Scenario 2 57.24
(assumes unadjusted exit poll (Kerry 52-47%)
________________________________________________________________________
2006
Democratic
candidate 7470 (56.37%)
Republican
candidate 5476 (41.33%)
Other 305 (2.30%)
True Vote match to the unadjusted exit poll
|
Voted 04 |
Mix |
Dem |
Rep |
Other |
|
Kerry |
48.5% |
93% |
6% |
1% |
|
Bush |
46.5% |
17% |
80% |
3% |
|
Other |
1% |
67% |
13% |
20% |
|
DNV |
4% |
67% |
27% |
6% |
|
TOTAL |
100% |
56.36% |
41.32% |
2.32% |
CNN 7:07 pm National Exit Poll (10207 respondents)
The adjustment begins:
Kerry return voter mix was reduced by 3.5%
1) 0.5% went to Bush voters
2) Impossible 3.0% went to to returning third-party
voters
(1% voted
third-party in 2004)
|
Voted 04 |
Mix |
Dem |
Rep |
Other |
|
Kerry |
45.0% |
93% |
6% |
1% |
|
Bush |
47.0% |
17% |
82% |
1% |
|
Other |
4% |
67% |
23% |
10% |
|
DNV |
4% |
67% |
30% |
3% |
|
TOTAL |
100% |
55.20% |
43.36% |
1.44% |
CNN Final National Exit Poll (13251 respondents)
1) Reduce Kerry return voter mix to 43%
2) Reduce Democratic share of returning Kerry voters
to 92%
3) Increase Bush return voter mix to 49%
4) Reduce Democratic share of returning Bush voters
to 15%
|
Voted 04 |
Mix |
Dem |
Rep |
Other |
|
Kerry |
43% |
92% |
7% |
1% |
|
Bush |
49% |
15% |
83% |
2% |
|
Other |
4% |
66% |
23% |
11% |
|
DNV |
4% |
66% |
32% |
2% |
|
TOTAL |
100% |
52.19% |
45.88% |
1.93% |
________________________________________________________________________
2008
(forced to match the recorded vote; impossible returning Bush and Other voters)
Implied 2004 Total Mix Obama McCain Other Obama McCain Other
Vote DNV 17.08 13% 71% 27% 2% 12.1 4.6 0.3
42.5% Kerry 48.61 37% 89% 9% 2% 43.3 4.4 1.0
52.9% Bush 60.43 46% 17% 82% 1% 10.3 49.6 0.6
4.6% Other 5.25 4% 66% 24% 10% 3.5 1.3 0.5
114.3 Total 131.37 100% 52.62% 45.52% 1.86% 69.13 59.80 2.44
Scenario 1 (implausible): returning voter mix based on the recorded 2004 vote (Bush 50.73-Kerry 48.27%).
Obama wins by 16.8m: 75.0-58.2 (55.4-43.0%)
2008 Calculated
Vote
2004 Record Unctd Cast Deaths Alive Turnout Voted Mix Obama McCain Other
DNV
19.42 14.3% 71% 27% 2%
Kerry 59.03 2.58 61.61 2.96 58.65 96.9% 56.85 42.0% 89% 9% 2%
Bush 62.04 0.83 62.87 3.02 59.85 96.9% 58.01 42.8% 17% 82% 1%
Other 1.23 0.03 1.26 0.06 1.20 96.9% 1.16 0.86% 66% 24% 10%
Total 122.30 3.45 125.74 6.04 119.70 116.0 135.43 100% 55.38% 42.98% 1.64%
Cast 135.43
75.01 58.20 2.22
Recorded 52.87% 45.62% 1.51%
131.37 69.46 59.94 1.98
Scenario 2 (plausible): returning voter mix based on the unadjusted 2004 exit poll (Kerry 52-Bush 47%).
Obama wins by 21.8m: 77.5-55.7 (57.2-41.1%)
2008 Calculated
Vote
DNV
19.42 14.3% 71% 27% 2%
Kerry 63.59 1.79 65.38 3.14 62.25 96.9% 60.33 44.5% 89% 9% 2%
Bush 57.47 1.62 59.09 2.84 56.26 96.9% 54.52 40.3% 17% 82% 1%
Other 1.23 0.03 1.26 0.06 1.20 96.9% 1.16 0.86% 66% 24% 10%
Total 122.30 3.45 125.74 6.04 119.70 116.0 135.43 100% 57.24% 41.10% 1.67%
Cast 135.43
77.52 55.66 2.26
Recorded 52.87% 45.62% 1.51%
131.37 69.46 59.94 1.98
