2012 Presidential True Vote Forecast Model 4/25/12
 Share
The version of the browser you are using is no longer supported. Please upgrade to a supported browser.Dismiss

 
$
%
123
 
 
 
 
 
 
 
 
 
 
 
 
 
 
A
1
The 2012 Presidential True Vote and Election Fraud Simulation Model
2
3
Richard Charnin
4
5
Click for latest version:
6
https://docs.google.com/spreadsheet/ccc?key=0AjAk1JUWDMyRdDQzLWJTdlppakNRNDlMakhhMGdGa0E#gid=13
7
8
Pre-election Polls and the”Horse Race”
9
10
At the Real Clear Politics (RCP)website, there are currently 21 Obama vs. Romney state polls listed (mostly battleground states). Recorded 2008 vote shares will be used in the model until polling data becomes available.
11
http://www.realclearpolitics.com/epolls/latest_polls/elections/
12
13
Obama currently leads the RCP National poll average by 47.7-43.8%. He also leads the aggregate weighted state poll average by 49.5-44.1%. But undecided voters usually break for the challenger. If the election were held today, he would have a 95% win probability with 300-320 EV.
14
15
Media pundits and pollsters only project the recorded vote – and they are usually right. They know there will be fraud, so they prepare you for it. The RV polls are transformed to LVs to promote an artificial “horse race”. The pundits want to predict the recorded vote. The closer they are, the better they look. But they never mention that it’s the fraud factor that gets them close.
16
17
Virtually all of the current national polls are of Registered Voters (RV). An exception is Rasmussen, a GOP pollster, whose daily tracking poll is a Likely Voter (LV) subset of the RV.
18
19
After allocating undecided voters, RV polls have closely matched the unadjusted exit polls and the True Vote Model. The Democrats always do better in RV polls than in the LV subsets.
20
21
One month before the election, pollsters convert from RV to LV polls. The Likely Voter Cutoff Model effectively understates the potential turnout of millions of new Democratic voters. LV polls are usually good predictors of the fraudulent recorded vote.
22
23
1988-2008 Exit Poll Discrepancies
24
25
Based on the historic record, Obama needs at least 55% to overcome systemic built-in fraud. In 2008 Obama had a 58% weighted average in the unadjusted STATE exit polls (76,000 respondents. He had 61% in the unadjusted NATIONAL Exit Poll (a 17,836 respondent subset of the state polls).
26
27
But for the same 17,836 respondents, CNN shows that he had just a 52.9% share. The FINAL National Exit poll was forced to match the recorded share. Obama’s TRUE 18% state aggregate exit poll margin was reduced to 7.5% But that’s to be expected; all finals are forced to match the recorded vote.
28
29
Election fraud cut 4% from the average 1988-2008 Democratic presidential share. In the 1988-2008 presidential elections, the Democrats won the unadjusted exit polls by 52-42%, but the recorded vote margin was just 48-46%.
30
31
Democratic True Vote = Recorded Vote + 4% Fraud Factor
32
33
Final exit polls are always forced to match the rigged recorded votes that were predicted by the final pre-election LV polls.
34
35
The True Vote Model
36
37
The TVM has two options for estimating returning voters: The default option assumes that returning 2008 voters are in proportion to the unadjusted exit poll aggregate (Obama won by 58-40.3%). This is the True Vote option.
38
39
The Recorded Vote option assumes that voters return in proportion to the 2008 recorded vote (won by Obama 52.9-45.6%). This is the Fraud option.
40
41
Obama wins the TVM by 51-49%. But that assumes returning 2008 voters are proportional to 2008 recorded vote (Obama had 52.9%). Assuming the 2008 unadjusted state exit polls (he had 58% in the polls as well as a 58% True Vote), Obama wins in 2012 by 55-45%. He has 377 EV with a 99.99% win probability.
42
43
A 1.25% annual voter mortality rate is assumed. The user can enter estimated turnout rates of living Obama and McCain voters.
44
45
The TVM can be used to project a given state as well as the national vote. Turnout rates and vote shares used in projecting the national vote are applied to each state in order to derive the national aggregate.
46
47
Sensitivity analysis
48
49
It is important in election modeling to view the effects of changes in input parameters. The TVM displays the effects of turnout rates and share of returning voters. Three tables are generated for nine scenario combinations of a) Obama and McCain turnout rates and b) shares of returning Obama and McCain voters. The tables provide resulting vote shares, margins and popular vote win probabilities.
50
51
Monte Carlo Simulation: 500 election trials
52
53
There are two options for running the simulation model. Both should be used and the results compared. The default option is to use the TVM projected state vote shares. The second is to use the projected state pre-election polls.
54
55
The simulation consists of 500 election trials. The electoral vote win probability is percentage of winning election trials.
56
57
The projected state vote share is the sum of the poll share and the undecided voter allocation (UVA). The model uses state vote share projections as input to the Normal Distribution function to determine the state win probability.
58
59
In each election trial, a random number (RND) between 0 and 1 is generated for each state and compared to Obama’s state win probability. If RND is greater than the win probability, the Republican wins the state. If RND is less than the win probability, Obama wins the state. The winner of the election trial is the candidate who has at least 270 electoral votes. The process is repeated in 500 election trials.
60
61
2008 State Exit Poll and recorded vote data is displayed in the ‘2008‘ worksheet. The latest state polls are listed in the ‘Polls” worksheet which will be used for trend analysis. The data is displayed graphically in the ‘PollChart’ worksheet. A histogram of the Monte Carlo Simulation (500 trials) is displayed in the ‘ObamaEVChart’ worksheet.
62
63
Electoral Votes and Win Probabilities
64
65
The Electoral Vote is calculated in three ways.
66
67
1. The snapshot EV is a simple summation of the state electoral votes. It could be misleading since there may be several very close elections which go one way.
68
2. The Theoretical EV is the product sum of the state electoral votes and win probabilities. A simulation or meta-analysis is not required to calculate the expected EV.
69
3. The Mean EV is the average electoral vote in the 500 simulated elections.
70
71
The Mean EV will be close to the Theoretical EV, illustrating the Law of Large Numbers. The snapshot EV will likely differ slightly from the Theoretical EV, depending on the number of state election projections that fall within the margin of error.
72
73
Obaama’s electoral vote win probability is the percentage of 500 simulated election trials that he won.
74
75
The national popular vote win probability is calculated as the state win probabilities: using the normal distribution. based on the final national share and the margin of error
76
77
The Fraud Factor
78
79
The combination of True Vote Model and state poll-based Monte Carlo Simulation enables the analyst to determine if the electoral and popular vote share estimates are plausible. The aggregate state poll shares can be compared to the default TVM (no fraud).
80
81
The TVM can be forced to match the aggregate poll projection by…
82
- Adjusting the vote shares (enter the incremental adjustment in cell C27). A red flag would be raised if the match required that Obama capture 85% of returning Obama voters while Romney gets 95% of returning McCain voters (a 10% net defection).
83
84
- Adjusting 2008 voter turnout in 2012 to force a match to the aggregate projected poll shares. For example, if McCain voter turnout is required to be 10-15% higher than Obama’s, that would also raise a red flag.
85
86
- Setting the recorded vote option (enter 1 in cell B18). If the resulting TVM vote shares indicate a close election and close to the projected poll shares, it would suggest that Romney has a good chance of winning.
87
88
Check the resulting electoral vote calculations and corresponding win probabilities.
89
90
91
92
93
94
95
Loading...
Main menu