TruthIsAll
09-07-2010, 07:12 PM
2010 House Generic Poll Forecasting Model
Richard Charnin (TruthIsAll)
Sept. 8, 2010
Link to the full analysis:
http://www.richardcharnin.com/2010GenericPollForecastingModel.htm
Generic polls provide a snapshot of the national electorate. As in forecasting of presidential and senate elections, the model assumes that the projected recorded vote is approximated by the latest likely voter (LV) polls. The LV polls are a subset of registered voter (RV) polls. Shares of undecided voters (UVA) are added to the RV poll average to derive a True Vote approximation. The fraud component accounts for the difference between the LV poll and the True Vote. The Democrats always do better in RV polls than in LV polls.
Gallup RV vs. Rasmussen LV
Do you believe the Gallup (RV) or Rasmussen (LV) poll?
Gallup
The latest Gallup RV poll indicates the race is tied at 46-46, with 8% undecided.
Based on Gallup, the model projects the GOP will have a mere 3 seat (219-216) margin in the House
Rasmussen
The latest Rasmussen poll gives the GOP a 48-36 lead, with 16% undecided.
Based on Rasmussen, the model projects the GOP will have a landslide 67 seat margin (251-184).
LV vs. RV polls
Of the latest 20 Generic polls, 7 are LV and 13 RV.
Latest 7 LV polls
The GOP leads the average by 47.1-37.9, which projects to 55.5-44.9, a 10.6% margin.
Based on the average projection, the GOP will have an approximate 51 seat margin (243-192).
Latest 13 RV polls
The GOP leads the average by 47.5-42.9, which projects to 52.6-47.4, a 5.2% margin.
Based on the average projection, the GOP will have an approximate 25 seat margin (230-205).
Election Fraud
The following model has proven to be quite accurate since 2004:
Recorded vote = LV projection = RV Poll + Undecided vote + Fraud
Solving for the fraud component, based on the latest RV and LV polls:
Recorded = 55.5 = RV (47.5) + UVA (5.1) + Fraud = 52.6 + Fraud
Fraud = LV projection (recorded) – RV projection (True)
Fraud = 2.9% = 55.5 - 52.6
2010
Of the 129 Generic Polls in 2010, 77 were RV and 49 LV (3 were not specified).
The GOP leads the LV average by 45.2-38.2, a 7.0% margin.
Rasmussen had 34 of the 47 LV polls (3500 sample) with the GOP leading by 45.0-36.8, an 8.2% margin.
All Rasmussen polls are LV.
The GOP leads the RV average by 44.6-41.2, a 3.4% margin.
Gallup had 28 RV polls (1600 sample) with the GOP leading by 46.4-45.1.
2008
Rasmussen had Obama leading in the final LV tracking LV poll by 51-46, or 52.0-46.5 after allocating undecided voters.
Gallup had Obama leading in the final RV tracking poll by 52-41. Allocating undecided voters, the projection was 56-42.5
Zogby had Obama leading in the final LV tracking poll by 51-44. Allocating undecided voters, the projection was 53.5-45.0
Obama had 52.9-45.6 recorded. The True Vote Model indicated that he had 57-58%.
2006
In the 2006 Midterms, the Generic Poll Trend Model allocated 60% to the Democrats. The linear regression trend projected a 56.4% Democratic share.
The unadjusted 2006 National Exit Poll was an exact match to the projection: 56.4%.
But the CNN Final Exit poll was forced to match the recorded vote: the Democratic share was reduced to 52.6%.
It is estimated that fraud cost the Democrats approximately 15 House seats or 4 seats per each one percent decline in vote share.
Projected recorded share = RV Poll + Undecided voter allocation (UVA) - Fraud Component
Democratic share = 52.6 = 52.0 + 4.4 - Fraud
Fraud = 3.8%
120 Generic Poll Linear Regression Trend
Dem = 46.98 + .0419x
Rep = 38.06 + .0047x
Substituting x = 120 and allocating 60% of the undecided vote (UVA) to the Democrats:
Trend + UVA = Projection
Dem = 52.01 + 4.42 = 56.43%
Rep = 38.62 + 2.95 = 41.57%
Richard Charnin (TruthIsAll)
Sept. 8, 2010
Link to the full analysis:
http://www.richardcharnin.com/2010GenericPollForecastingModel.htm
Generic polls provide a snapshot of the national electorate. As in forecasting of presidential and senate elections, the model assumes that the projected recorded vote is approximated by the latest likely voter (LV) polls. The LV polls are a subset of registered voter (RV) polls. Shares of undecided voters (UVA) are added to the RV poll average to derive a True Vote approximation. The fraud component accounts for the difference between the LV poll and the True Vote. The Democrats always do better in RV polls than in LV polls.
Gallup RV vs. Rasmussen LV
Do you believe the Gallup (RV) or Rasmussen (LV) poll?
Gallup
The latest Gallup RV poll indicates the race is tied at 46-46, with 8% undecided.
Based on Gallup, the model projects the GOP will have a mere 3 seat (219-216) margin in the House
Rasmussen
The latest Rasmussen poll gives the GOP a 48-36 lead, with 16% undecided.
Based on Rasmussen, the model projects the GOP will have a landslide 67 seat margin (251-184).
LV vs. RV polls
Of the latest 20 Generic polls, 7 are LV and 13 RV.
Latest 7 LV polls
The GOP leads the average by 47.1-37.9, which projects to 55.5-44.9, a 10.6% margin.
Based on the average projection, the GOP will have an approximate 51 seat margin (243-192).
Latest 13 RV polls
The GOP leads the average by 47.5-42.9, which projects to 52.6-47.4, a 5.2% margin.
Based on the average projection, the GOP will have an approximate 25 seat margin (230-205).
Election Fraud
The following model has proven to be quite accurate since 2004:
Recorded vote = LV projection = RV Poll + Undecided vote + Fraud
Solving for the fraud component, based on the latest RV and LV polls:
Recorded = 55.5 = RV (47.5) + UVA (5.1) + Fraud = 52.6 + Fraud
Fraud = LV projection (recorded) – RV projection (True)
Fraud = 2.9% = 55.5 - 52.6
2010
Of the 129 Generic Polls in 2010, 77 were RV and 49 LV (3 were not specified).
The GOP leads the LV average by 45.2-38.2, a 7.0% margin.
Rasmussen had 34 of the 47 LV polls (3500 sample) with the GOP leading by 45.0-36.8, an 8.2% margin.
All Rasmussen polls are LV.
The GOP leads the RV average by 44.6-41.2, a 3.4% margin.
Gallup had 28 RV polls (1600 sample) with the GOP leading by 46.4-45.1.
2008
Rasmussen had Obama leading in the final LV tracking LV poll by 51-46, or 52.0-46.5 after allocating undecided voters.
Gallup had Obama leading in the final RV tracking poll by 52-41. Allocating undecided voters, the projection was 56-42.5
Zogby had Obama leading in the final LV tracking poll by 51-44. Allocating undecided voters, the projection was 53.5-45.0
Obama had 52.9-45.6 recorded. The True Vote Model indicated that he had 57-58%.
2006
In the 2006 Midterms, the Generic Poll Trend Model allocated 60% to the Democrats. The linear regression trend projected a 56.4% Democratic share.
The unadjusted 2006 National Exit Poll was an exact match to the projection: 56.4%.
But the CNN Final Exit poll was forced to match the recorded vote: the Democratic share was reduced to 52.6%.
It is estimated that fraud cost the Democrats approximately 15 House seats or 4 seats per each one percent decline in vote share.
Projected recorded share = RV Poll + Undecided voter allocation (UVA) - Fraud Component
Democratic share = 52.6 = 52.0 + 4.4 - Fraud
Fraud = 3.8%
120 Generic Poll Linear Regression Trend
Dem = 46.98 + .0419x
Rep = 38.06 + .0047x
Substituting x = 120 and allocating 60% of the undecided vote (UVA) to the Democrats:
Trend + UVA = Projection
Dem = 52.01 + 4.42 = 56.43%
Rep = 38.62 + 2.95 = 41.57%