TruthIsAll
07-15-2010, 08:46 AM
Open Letter to Nate Silver (part 2): Zogby vs. Rasmussen, RV vs. LV, Simulation Mean vs. Expected EV, Recorded vs. True Vote
Richard Charnin (TruthIsAll)
July 15, 2010
This is an update to my open letter to you of a few days ago. The purpose is to further discuss a) the difference between 2008 pre-election registered voter (RV) polls and likely voter (LV) polls for forecasting, b) Zogby’s poll vs. selected GOP-leaning polls and c) the close match between the RV polls and the post-election True Vote Model.
I have added two new tables for you to review.
Table 5 is a comparison of final RV and LV polls
The average LV poll had Obama winning by 50.3-44.0 before allocating undecided voters (UVA) and 53.4-45.1 after UVA.
The average RV poll had Obama winning by 53.3-39.5 before UVA and 57.6-40.9 after UVA.
Zogby’s LV poll had Obama winning by 54-43 before UVA and 55.1-43.4 after UVA.
Consider the final ABC and Gallup RV Polls (combined 5293 sample, 1.8% MoE).
They had Obama winning by 53.5-40.5 before UVA and 56.9-41.6 after UVA.
You rank Zogby dead last, yet his LV poll numbers are right in the middle of the RV and LV groups.
He is closer to ABC and Gallup than Rasmussen, Hotline and FOX.
You have lowered Rasmussen’s ranking but you still rank him much higher than Zogby.
Rasmussen has a strong GOP bias. Hotline, FOX and Battleground also lean to the GOP.
Do you have any evidence that Zogby’s polls are biased?
Do you still feel that you are justified in ranking Zogby last?
Table 6 displays the post-election True Vote Model.
It closely matches the RV projections.
It proves that the NEP returning voter mix is bogus.
My final 2008 Election Model gave Obama 53.1%. The 5000 election- trial Monte Carlo EV simulation produced a 365.8 mean EV.
The convergence of the mean to the expected value illustrates the Law of Large Numbers.
The expected value is given by the simple summation: EV = å Win probability (i) * EV (i), where i=1,51 states
Obama had an expected 365.3 electoral votes, matching his recorded total.
The Election Model exactly matched the recorded EV and was within 0.2% of the popular vote.
But it was wrong. It understated Obama’s True Vote.
The final state polls were LVs, not RVs.
Do you still believe that Obama’s 52.9% recorded share reflects the True Vote?
Do you still think that Obama had just 365 electoral votes?
The True Vote model indicates that Obama had close to 58% and over 420 EV!
[code]
TABLE 5:
Final RV vs. LV Poll Projections
Projection: Allocate Undecided
75% 25%
LV Poll Size Date Obama McCain Margin Obama McCain Margin
FOX 971 11/02 - 11/03 50 43 7 54.1 44.4 9.8
Hotline 882 10/31 - 11/02 50 45 5 52.6 45.9 6.8
Rasmuss 3000 10/31 - 11/02 51 46 5 52.1 46.4 5.8
CNN 1017 10/30 - 11/01 51 43 8 54.4 44.1 10.3
Pew 2587 10/30 - 11/01 49 42 7 54.6 43.9 10.8
Average 1872 10/30 - 11/03 50.3 44.0 6.3 53.4 45.1 8.4
Zogby(LV)1201 11/01 - 11/03 54 43 11 55.1 43.4 11.8
RV Poll Size Date Obama McCain Margin Obama McCain Margin
Gallup 2847 10/31 - 11/02 53 40 13 57.1 41.4 15.8
ABC/WP 2446 10/31 - 11/02 54 41 13 56.6 41.9 14.8
CBS 1005 10/28 - 10/31 54 41 13 56.6 41.9 14.8
Pew 1325 10/23 - 10/26 52 36 16 59.9 38.6 21.3
Total 7623 10/23 - 11/02 53.3 39.5 13.8 57.6 40.9 16.6
Gallup+ABC
5293 10/31 - 11/02 53.5 40.5 13.0 56.9 41.6 15.3
2-pty 57.7 42.3 15.5
MoE= 1.96 * (sqrt(p) * (1-p)/n))
MoE: 1.8%
TABLE 6
2008 TRUE VOTE ANALYSIS
National 2008 True Vote Analysis
2004 Turnout in 2008 Unctd / stuffed
Cast 0 Unctd Alive Cast OfficialUnctd Mortal Kerry Bush Kerry Bush Other
125.7 122.3 3.4 119.4 132.6 131.4 1.2 6.6 97% 97% 75% 25% 0%
- 97.3% 2.7% 95.0% - 99.1% 0.9% 5.0% - - 0% 100% -
National Vote (mil) 422 EV Pct Share (%) Vote (mil)
MoE 2004 Cast Recorded Alive Turnout Mix Obama McCain Other Obama McCain Other Turnout
1.6% DNV - - - 16.4 12.4 71.0 27.0 2.0 11.7 4.4 0.33
1.1% Kerry 67.1 59.0 63.8 61.9 46.8 89.0 10.0 1.0 55.1 6.2 0.62 97%
1.3% Bush 57.0 62.0 54.1 52.5 39.7 17.0 82.0 1.0 8.9 43.0 0.52 97%
1.6% Other 0.0 1.2 1.6 1.5 1.1 72.0 17.0 11.0 1.1 0.3 0.17 97%
True 125.7 122.3 119.5 132.3 100.0 58.0 40.8 1.2 76.7 53.9 1.64 97%
2004 Kerry Bush Other Recorded 52.9 45.6 1.5 69.5 59.9 1.98 131.4
Record 48.3 50.7 1.0 Diff 5.1 -4.9 -0.3 7.3 -6.0 -0.34
Cast 49.4 49.6 1.0 Exit Poll na
ExitP 52.0 47.0 1.0
Sensitivity Analysis
Bush Kerry voter turnout Share of Obama Share of DNV
turnout 90% 92% 94% 96% 98% Bush 69% 70% 71% 72% 73%
Obama Share (%) Obama Share (%)
90% 58.9 59.1 59.3 59.5 59.6 19% 58.6 58.7 58.8 58.9 59.0
92% 58.5 58.7 58.8 59.0 59.2 18% 58.2 58.3 58.4 58.5 58.7
94% 58.1 58.2 58.4 58.6 58.8 17% 57.8 57.9 58.0 58.1 58.3
96% 57.6 57.8 58.0 58.1 58.3 16% 57.4 57.5 57.6 57.7 57.9
98% 57.2 57.4 57.5 57.7 57.9 15% 57.0 57.1 57.2 57.3 57.5
Obama Margin (mil.) Obama Margin (mil.)
90% 25.4 25.8 26.3 26.7 27.2 19% 24.3 24.6 24.9 25.3 25.6
92% 24.2 24.6 25.1 25.5 26.0 18% 23.2 23.5 23.9 24.2 24.5
94% 23.0 23.5 23.9 24.4 24.8 17% 22.2 22.5 22.8 23.2 23.5
96% 21.8 22.3 22.7 23.2 23.6 16% 21.1 21.4 21.8 22.1 22.4
98% 20.7 21.1 21.6 22.0 22.5 15% 20.1 20.4 20.7 21.1 21.4
Obama Electoral Vote Obama Electoral Vote
90% 428 428 428 428 428 19% 428 428 428 428 428
92% 428 428 428 428 428 18% 422 422 422 422 422
94% 422 422 422 428 428 17% 408 422 422 422 422
96% 408 422 422 422 422 16% 397 408 408 408 419
98% 389 397 408 408 411 15% 374 374 389 408 408
MoE 1.0% 0.9% 0.8% 0.7% 0.5% MoE 1.6% 1.6% 1.6% 1.6% 1.5%
Richard Charnin (TruthIsAll)
July 15, 2010
This is an update to my open letter to you of a few days ago. The purpose is to further discuss a) the difference between 2008 pre-election registered voter (RV) polls and likely voter (LV) polls for forecasting, b) Zogby’s poll vs. selected GOP-leaning polls and c) the close match between the RV polls and the post-election True Vote Model.
I have added two new tables for you to review.
Table 5 is a comparison of final RV and LV polls
The average LV poll had Obama winning by 50.3-44.0 before allocating undecided voters (UVA) and 53.4-45.1 after UVA.
The average RV poll had Obama winning by 53.3-39.5 before UVA and 57.6-40.9 after UVA.
Zogby’s LV poll had Obama winning by 54-43 before UVA and 55.1-43.4 after UVA.
Consider the final ABC and Gallup RV Polls (combined 5293 sample, 1.8% MoE).
They had Obama winning by 53.5-40.5 before UVA and 56.9-41.6 after UVA.
You rank Zogby dead last, yet his LV poll numbers are right in the middle of the RV and LV groups.
He is closer to ABC and Gallup than Rasmussen, Hotline and FOX.
You have lowered Rasmussen’s ranking but you still rank him much higher than Zogby.
Rasmussen has a strong GOP bias. Hotline, FOX and Battleground also lean to the GOP.
Do you have any evidence that Zogby’s polls are biased?
Do you still feel that you are justified in ranking Zogby last?
Table 6 displays the post-election True Vote Model.
It closely matches the RV projections.
It proves that the NEP returning voter mix is bogus.
My final 2008 Election Model gave Obama 53.1%. The 5000 election- trial Monte Carlo EV simulation produced a 365.8 mean EV.
The convergence of the mean to the expected value illustrates the Law of Large Numbers.
The expected value is given by the simple summation: EV = å Win probability (i) * EV (i), where i=1,51 states
Obama had an expected 365.3 electoral votes, matching his recorded total.
The Election Model exactly matched the recorded EV and was within 0.2% of the popular vote.
But it was wrong. It understated Obama’s True Vote.
The final state polls were LVs, not RVs.
Do you still believe that Obama’s 52.9% recorded share reflects the True Vote?
Do you still think that Obama had just 365 electoral votes?
The True Vote model indicates that Obama had close to 58% and over 420 EV!
[code]
TABLE 5:
Final RV vs. LV Poll Projections
Projection: Allocate Undecided
75% 25%
LV Poll Size Date Obama McCain Margin Obama McCain Margin
FOX 971 11/02 - 11/03 50 43 7 54.1 44.4 9.8
Hotline 882 10/31 - 11/02 50 45 5 52.6 45.9 6.8
Rasmuss 3000 10/31 - 11/02 51 46 5 52.1 46.4 5.8
CNN 1017 10/30 - 11/01 51 43 8 54.4 44.1 10.3
Pew 2587 10/30 - 11/01 49 42 7 54.6 43.9 10.8
Average 1872 10/30 - 11/03 50.3 44.0 6.3 53.4 45.1 8.4
Zogby(LV)1201 11/01 - 11/03 54 43 11 55.1 43.4 11.8
RV Poll Size Date Obama McCain Margin Obama McCain Margin
Gallup 2847 10/31 - 11/02 53 40 13 57.1 41.4 15.8
ABC/WP 2446 10/31 - 11/02 54 41 13 56.6 41.9 14.8
CBS 1005 10/28 - 10/31 54 41 13 56.6 41.9 14.8
Pew 1325 10/23 - 10/26 52 36 16 59.9 38.6 21.3
Total 7623 10/23 - 11/02 53.3 39.5 13.8 57.6 40.9 16.6
Gallup+ABC
5293 10/31 - 11/02 53.5 40.5 13.0 56.9 41.6 15.3
2-pty 57.7 42.3 15.5
MoE= 1.96 * (sqrt(p) * (1-p)/n))
MoE: 1.8%
TABLE 6
2008 TRUE VOTE ANALYSIS
National 2008 True Vote Analysis
2004 Turnout in 2008 Unctd / stuffed
Cast 0 Unctd Alive Cast OfficialUnctd Mortal Kerry Bush Kerry Bush Other
125.7 122.3 3.4 119.4 132.6 131.4 1.2 6.6 97% 97% 75% 25% 0%
- 97.3% 2.7% 95.0% - 99.1% 0.9% 5.0% - - 0% 100% -
National Vote (mil) 422 EV Pct Share (%) Vote (mil)
MoE 2004 Cast Recorded Alive Turnout Mix Obama McCain Other Obama McCain Other Turnout
1.6% DNV - - - 16.4 12.4 71.0 27.0 2.0 11.7 4.4 0.33
1.1% Kerry 67.1 59.0 63.8 61.9 46.8 89.0 10.0 1.0 55.1 6.2 0.62 97%
1.3% Bush 57.0 62.0 54.1 52.5 39.7 17.0 82.0 1.0 8.9 43.0 0.52 97%
1.6% Other 0.0 1.2 1.6 1.5 1.1 72.0 17.0 11.0 1.1 0.3 0.17 97%
True 125.7 122.3 119.5 132.3 100.0 58.0 40.8 1.2 76.7 53.9 1.64 97%
2004 Kerry Bush Other Recorded 52.9 45.6 1.5 69.5 59.9 1.98 131.4
Record 48.3 50.7 1.0 Diff 5.1 -4.9 -0.3 7.3 -6.0 -0.34
Cast 49.4 49.6 1.0 Exit Poll na
ExitP 52.0 47.0 1.0
Sensitivity Analysis
Bush Kerry voter turnout Share of Obama Share of DNV
turnout 90% 92% 94% 96% 98% Bush 69% 70% 71% 72% 73%
Obama Share (%) Obama Share (%)
90% 58.9 59.1 59.3 59.5 59.6 19% 58.6 58.7 58.8 58.9 59.0
92% 58.5 58.7 58.8 59.0 59.2 18% 58.2 58.3 58.4 58.5 58.7
94% 58.1 58.2 58.4 58.6 58.8 17% 57.8 57.9 58.0 58.1 58.3
96% 57.6 57.8 58.0 58.1 58.3 16% 57.4 57.5 57.6 57.7 57.9
98% 57.2 57.4 57.5 57.7 57.9 15% 57.0 57.1 57.2 57.3 57.5
Obama Margin (mil.) Obama Margin (mil.)
90% 25.4 25.8 26.3 26.7 27.2 19% 24.3 24.6 24.9 25.3 25.6
92% 24.2 24.6 25.1 25.5 26.0 18% 23.2 23.5 23.9 24.2 24.5
94% 23.0 23.5 23.9 24.4 24.8 17% 22.2 22.5 22.8 23.2 23.5
96% 21.8 22.3 22.7 23.2 23.6 16% 21.1 21.4 21.8 22.1 22.4
98% 20.7 21.1 21.6 22.0 22.5 15% 20.1 20.4 20.7 21.1 21.4
Obama Electoral Vote Obama Electoral Vote
90% 428 428 428 428 428 19% 428 428 428 428 428
92% 428 428 428 428 428 18% 422 422 422 422 422
94% 422 422 422 428 428 17% 408 422 422 422 422
96% 408 422 422 422 422 16% 397 408 408 408 419
98% 389 397 408 408 411 15% 374 374 389 408 408
MoE 1.0% 0.9% 0.8% 0.7% 0.5% MoE 1.6% 1.6% 1.6% 1.6% 1.5%