The 2008 Presidential Election Polling Exam

Jan. 3, 2009

A multiple choice exam to test your knowledge of pre-election and exit polls.
The answers are several screens below the last question.

1. The latest recorded vote count (to the nearest million)?
a) 121 b) 127 c) 131

2. Obama's Electoral Vote?
a) 345 b) 365 c) 367

3. Obama's vote share as of today?
a) 52.3 b) 52.6 c) 52.9

4) Obama's share of the 10 million votes recorded since Election Day (%)?
a) 52.1 b) 55.5 c) 59.2

5) Obama's average LV (likely voter) pre-election poll margin (%)?
a) 5 b) 7 c) 8

6) Obama's average RV (registered voter) poll margin (%)?
a) 6 b) 8 c) 10

7) Assuming Obama was the challenger,
what percentage of UNDECIDED votes could he expect to win?
a) 50-60 b) 60-70 c) 70+

8) The National Exit Poll is always forced to match the recorded vote.
a) True b) False

9) Assuming a) the 2004 RECORDED vote was the TRUE VOTE and
b)the 2008 National Exit Poll (NEP) shares of new and returning 2004 voters are correct,
what percentage of living Bush voters returned to vote in 2008?
a) 90% b) 96% c) 102%

10) Assuming a) the UNADJUSTED 2004 EXIT POLL was the TRUE VOTE and
b) the NEP shares of new and returning 2004 voters are correct,
what percentage of living Bush voters returned to vote in 2008?
a) 96% b) 104% c) 110%

11) Assuming a) the RECORDED 2004 vote was the TRUE VOTE,
b) the NEP shares of new and returning 2004 voters are correct and
c) an equal 95% turnout of Bush and Kerry voters,
Obama's True vote share is?
a) 52% b) 53% c) 55%

12) Assuming a) the UNADJUSTED 2004 EXIT POLL was the TRUE VOTE,
b) the NEP shares of new and returning 2004 voters are correct, and
c) an equal 95% turnout of Bush and Kerry voters,
what is Obama's True vote share?
a) 53% b) 55% c) 57%

13) What is Obama's RECORDED vote margin (in millions)?
a) 7.5 b) 8.5 c) 9.5

14) Assuming a) the RECORDED 2004 vote was the TRUE VOTE,
b) the NEP shares of new and returning 2004 voters are correct, and
c) an equal 95% turnout of Bush and Kerry voters,
what is Obama's True Vote margin?
a) 10 b) 13 c) 17

15) Assuming a) the UNADJUSTED 2004 EXIT POLL was the TRUE VOTE,
b) the NEP shares of new and returning 2004 voters are correct, and
c) an equal 95% turnout of Bush and Kerry voters,
what is Obama's True Vote margin?
a) 10 b) 15 c) 22

16) The Final NEP is ALWAYS FORCED TO MATCH the official, RECORDED vote.
If the Final indicates that more Bush 2004 voters returned to vote
in 2008 than were still living, then
a) it's of no consequence
b) every poll has a margin of error
c) it indicates that the Final is not to be believed

17) If the Final 2008 NEP indicates an IMPOSSIBLE number of returning
Bush and third-party voters, then
a) I would just accept it
b) I would not trust the Final 2008 NEP
c) I would not trust the 2008 recorded vote
d) I would not trust the Final 2008 NEP or the 2008 recorded vote

18) If the Final 2004 NEP indicates an IMPOSSIBLE number of returning
Bush and third-party voters, then
a) I would just accept the Final 2004 NEP and move on
b) I would not trust the Final 2004 NEP
c) I would not trust the 2004 recorded vote
d) I would not trust the Final 2004 NEP or the 2004 recorded vote

19) In every election, millions of votes are UNCOUNTED; 70-80% are Democratic.
What does that indicate about the RECORDED VOTE?
a) The recorded vote does not reflect the True Vote
b) The Democratic margin is least 1-2% higher than the official margin
c) both
d) neither

20) Given 51 state win probabilities, the theoretical EXPECTED EV is determined by
a) the sum of the electoral votes allocated to the projected winner of each state
b) the sum of the win probabilities times the electoral votes for each state
c) a meta-analysis of billions of state win combinations

21) The Election Model Monte Carlo Simulation calculated the AVERAGE EV based on
a) the average electoral vote of 5000+ trial simulations
b) the national projected popular vote
c) the state projected popular votes

22) The Monte Carlo Simulation calculated the EV WIN PROBABILITY based on
a) the state win probabilities
b) the ratio of winning trials
c) both
d) neither

23) There were 5000 Election Model Monte Carlo ELECTION TRIALS. Obama won
a) 4900
b) 4500
c) 5000

24) If a 10,000 trial Monte Carlo EV simulation produces 348 expected EV
for Obama with a 95% EV win probability,
a) the EV win probability is incompatible with the expected EV
b) certain factors skewed the simulation results
c) both of the above are true
d) it's impossible to draw a conclusion about the methodology

25) If you correctly answered at least 18 questions (72%), you're a
a) tin-foil-hat-wearing election fraud conspiracy nut
b) serious quantitative election analyst
c) lucky guesser



































Answers:
1 b
2 b
3 b
4 c
5 b
6 c
7 c
8 a
9 c
10 c
11 c
12 c
13 c
14 c
15 c
16 c
17 d
18 d
19 c
20 b
21 a
22 c
23 c
24 c
25 b or c

div style="width: 840px;font-family: Arial,Times New Roman;font-size: 16.5px;line-height: 1.25;"]
[div style="font-size: 24px;font-style: italic;font-weight:bold;"]2008 Election Analysis: A Compendium of Links[/quote]
[link:www.truthisall.net/|TruthIsAll]source: [link:www.geocities.com/electionmodel/2008ElectionAnalysisLinks.htm|http://www.geocities.com/electionmodel/2008ElectionAnalysisLinks.htm]

January 3,2009


Popular and Electoral Vote Projections

[link:www.geocities.com/electionmodel/2008ElectionCalculator.htm|The Election Calculator]

The preliminary May 23, 2008 model projection indicated that Obama would win by 12 million votes: 71-59m (54.1-44.7%). The model estimated the number of returning 2004 voters and vote shares to project the popular vote The number of returning 2004 voters was estimated by adjusting the 2004 recorded vote for a 4.8% voter mortality rate, 3.45 million uncounted votes and an estimated 95% turnout of 2004 voters in 2008. The Obama and McCain projected vote shares of returning and new voters were close to the preliminary, unadjusted 2004 National Exit Poll estimates for Kerry and Bush, respectively.

[link:www.geocities.com/electionmodel/2008ElectionModel.htm|The Election Model]

This Monte Carlo electoral vote simulation projected 365.3 expected electoral votes for Obama and a 53.1-44.9% share. He won by 365–173 EV with a 69.5–59.9m popular vote margin (52.87–45.62%). The base case assumption was that Obama would win 60% of late undecided voters. A 75% undecided voter allocation produced a 53.8% share and 379.5 expected EV. Pollsters typically allocate 70–90% of the late undecided vote to the challenger depending on the incumbent’s performance. McCain was the de facto incumbent; Bush approval was 22%.

[link:www.democraticunderground.com/discuss/duboard.php?az=view_all&address=203x510632|The Election Model projected 365.3 expected electoral votes — but not the True Vote]

Although the model exactly matched the electoral vote and was within 0.2% of the popular vote share, it underestimated the True Vote. But a post-election sensitivity analysis using Final 2008 NEP vote shares with a plausible returning voter mix indicated that Obama’s True vote share was 2–4% higher than the recorded share.


Post-Election Analysis

[link:www.democraticunderground.com/discuss/duboard.php?az=view_all&address=108x134587|A Conversation about the 2008 election]

A one on one discussion summarizes the statistical anomalies. The Final 2008 National Exit Poll provides the “tell”. It’s standard procedure for the Final NEP to “adjust” demographic weights and vote shares and force a match to the recorded vote. Unfortunately, an impossible mix of returning voters was necessary in order to force the match — just as it was in 2004.

[link:www.democraticunderground.com/discuss/duboard.php?az=view_all&address=203x510524|Landslide Denied]

The tremendous GOTV and new voter registration effort was not reflected in the recorded vote, a 9 million increase from 2004 compared to 17 million in 2004. An analysis of uncounted votes and exit poll discrepancies in the1988-2004 presidential elections revealed some very interesting information. In the 4 elections from1988 to 2000, the average unadjusted state exit poll aggregate was within 1% of the recorded vote - after uncounted votes were included. Butt 2004 was different in kind and scope: including the uncounted votes did not make up the difference. HAVA (Help America Vote Act) was passed during the first Bush term.

[link:www.geocities.com/electionmodel/Final2008NEPScenarios.htm|2008 National Exit Poll Does Not Compute]

The National Exit Poll “Voted in 2004” returning voter mix (46 Bush / 37 Kerry / 4 Other) implies that Bush voters comprised 46% (60.3m) of the recorded 131.07m vote. Bush had 62.0 million recorded votes in 2004 and approximately 3.0m died, so there were only 59.0m potential Bush voters in 2008. Assuming a 95% turnout, 56m voted. Where did the 4.3m Bush voters come from? The Final NEP also implies that 5.2m (4%) were returning third-party voters, but there were 1.2m third-party votes in 2004. Where did the 4m third-party voters come from? One can only conclude that since an impossible Final 2008 NEP was forced to match the recorded vote, the recorded vote was also impossible.

[link:www.geocities.com/electionmodel/2008StatAnomalies.htm|Statistical Anomalies]

The 2008 Election Calculator model calculated the True vote based on returning 2004 voters and Final 2008 National Exit Poll vote shares. It indicates that Obama’s True Vote was more than double his recorded 9.5m vote margin. Anomalies abound in the national and state pre-election polls, exit polls, late vote shares. The number of uncounted votes is still unknown. Assuming the 2004 True Vote (Kerry by 67–57m), then only 51m Bush voters returned to vote in 2008, a 9.3m discrepancy from the Final NEP.

[link:www.geocities.com/electionmodel/ElectionCalculator2008VoteMatch.htm|Matching to the 2008 Recorded Vote]

The 2008 National Exit Poll Bush/Kerry (46/37) returning voter mix, like the 2004 Bush/Gore (43/37) mix, was mathematically impossible. In order to match the recorded vote, both polls required about 6 million more returning Bush voters than were still living. The 2008 return voter mix anomaly is further confirmation that Kerry won. An impossible high returning Bush voter turnout and low Kerry turnout were required to match the 2008 recorded vote. Like Gore and Kerry, Obama’s True vote far exceeded his recorded vote.

In order to match the 2008 recorded vote, the NEP implied that Bush won by 53–43%. He won the official vote by 50.7–48.3% (62–59m). Because the returning voter mix was impossible, two returning voter scenarios were input to the Election Calculator with the goal of calculating the vote shares required to matching the vote: the 2004 recorded vote and unadjusted 2004 aggregate exit poll (Kerry won by 52–47%). The 2004 returning voter turnout required in 2008 in order to match the vote was impossible.

[link:www.democraticunderground.com/discuss/duboard.php?az=show_mesg&forum=108&topic_id=134606&mesg_id=134606|Using Excel Solver to Calculate the Required Vote Mix ]

The National Exit Poll asked respondents whom they voted for in 2004 as well as in 2008, but the unadjusted NEP vote shares did not match the official count. It never does. The Final NEP is always forced to match the official vote count. How do the pollsters adjust the mix and/or shares to achieve the match? The Excel Solver program uses a search algorithm (“goal-seeking”) to adjust the returning voter mix and force a match the official count. But the mix is impossible: required Bush voter turnout exceeds the number who actually voted in 2004.

[link:www.geocities.com/electionmodel/ObamaLandslide3D.htm|Obama Landslide in 3D]

Obama’s total vote share is a function of his share of returning Kerry, Bush and new voters. The Final NEP vote shares were 89%, 17% and 71%, respectively. Due to the margin of error, it is instructive to view the effects of incremental changes on the total vote. The Election Calculator sensitivity analysis shows that Obama did much better than the recorded margin; he may have won by more than 20 million votes. Two basic scenarios were considered in order to derive a plausible returning voter mix: a) the recorded 2004 vote (Bush 50.7–48.3%) and b) the unadjusted 2004 exit poll (Kerry 52–47%). The mix was calculated using voter mortality, uncounted votes and turnout rates. Obama won the recorded vote (conservative) scenario by 17.6 million: 75.4–57.8m (55.7–42.7%). He won the exit poll (most-likely) scenario by 22.6m: 77.9–55.3m (57.5–40.8%).

[link:www.geocities.com/electionmodel/2008ElectionSensitivityAnalysis.htm|Election Calculator Sensitivity Analysis]

All models consist of actual recorded data, assumptions (parameters), and calculations. Given that the Election Calculator (EC) mathematical computations are correct, the base case assumptions must closely reflect reality in order to calculate the True Vote,. The base case assumptions are best estimates taken from the following data sources: the 2004 and 2008 official recorded vote, voter mortality tables, historical returning voter turnout percentages, Census total votes cast, 2008 National Exit Poll vote shares and the unadjusted (WPE) Edison-Mitofsky 2004 state exit poll aggregate shares. Due to the margin of error in the data estimates, confidence in the model requires an examination of the effects of changes in the assumptions. The EC contains a comprehensive set of sensitivity analysis tables. Each table is a 5x5 matrix combination of two assumptions (variables). The impact of each combination on Obama’s vote share and margin is displayed in 25 matrix cells. It is very likely that the True Vote is located in one of the 25 cells; the best estimate is in the central cell. The range of plausible vote shares can be narrowed from 25 to 9 by focusing on the combinations of assumptions that lie within the margin of error.


Forecasting Methodology

[link:www.geocities.com/electionmodel/ProjectingEV.htm|Projecting the Electoral Vote and Win Probability]

Most election forecasters, media pundits and academics don’t apply basic probability, statistics and simulation methodology in forecasting the electoral vote and corresponding win probability. A meta-analysis or simulation is not required to calculate the expected electoral vote. Regardless of the particular method used to forecast the winner of each state, the corresponding state win probabilities are necessary in order to calculate the expected EV and win probability.

[link:www.geocities.com/electionmodel/2008ElectionModelChallenge.htm|Election Model: Monte Carlo Simulation]

The expected state EV is the win probability times the electoral vote. If the probability is 50% and the state has 20 EV, then each candidate gets 10 electoral votes. The Total Expected EV is just the sum of all the states. So the math is exceedingly simple. The tricky part is projecting the state vote shares using the latest polls. The Election Model allocates undecided voters to derive the projected 2-party vote. The state win probabilities are used in a 5000 election-trial Monte Carlo simulation. The probability that a candidate will win the EV is the number of winning election trials/5000.

[link:www.geocities.com/electionmodel/ElectionModelMonteCarlo.htm|Election Forecasting Models]

Includes the following:
. Time-series regression models vs. Monte Carlo polling simulation
. Final 2004 state and national projections confirmed by the exit polls
. Analysis of 2004 registered voter (RV) and likely voter (LV) polls
. Basic Polling Mathematics
. Overview of Monte Carlo Electoral Vote Simulation

[link:www.geocities.com/electionmodel/2008PrimariesLinks.htm|2008 Primaries: Footprints of Election Fraud]

[link:www.geocities.com/electionmodel/FurtherConfirmationOfaKerryLandslide.htm|Confirmation of a Kerry Landslide]

[link:www.geocities.com/electionmodel/TruthIsAllFAQResponse.htm|2004-2006 Election Fraud Analytics]

[link:www.geocities.com/electionmodel|2004 Election Model]


[/quote]

[div style="clear:left;line-height: 1.0"][/quote]