You are viewing an obsolete version of the DU website which is no longer supported by the Administrators. Visit The New DU.
Democratic Underground Latest Greatest Lobby Journals Search Options Help Login
Google

9/20 ELECTION MODEL (TIA): 98.5% OBAMA EV WIN PROBABILITY (4926 WINS/5000 SIMULATION TRIALS) [View All]

Printer-friendly format Printer-friendly format
Printer-friendly format Email this thread to a friend
Printer-friendly format Bookmark this thread
Home » Discuss » Topic Forums » Election Reform Donate to DU
tiptoe Donating Member (1000+ posts) Send PM | Profile | Ignore Sat Sep-20-08 08:33 PM
Original message
9/20 ELECTION MODEL (TIA): 98.5% OBAMA EV WIN PROBABILITY (4926 WINS/5000 SIMULATION TRIALS)
Advertisements [?]
Edited on Sat Sep-20-08 08:50 PM by tiptoe


2008 ELECTION MODEL
A  Monte Carlo  Electoral  Vote  Simulation



Updated: September 20

Press REFRESH after linking to a graph to view the latest update

  • Chart   State Poll Aggregate + Projection Trend
  • Chart   National 5-Poll Moving Average Projection
  • Chart   State vs. National: Vote Share Projection Trends
  • Chart   Battleground-State Polls
  • Chart   Battleground-State Win Probability
  • Chart   Obama Electoral Vote Simulation Frequency
  • Chart   Electoral Vote + Win Probability Trend
  • Chart   Electoral Vote + Projected Vote Share Trend
  • Chart   Undecided Voter Allocation + Win Probability
  • Chart   Monte Carlo Electoral Vote Simulation Trials
     2008 Election Model Fraud Analyzer 
  • Uncounted  &  Switched Votes
  • Chart   Effect on Obama Projected Vote Share
  • Chart   Effect on Obama Projected Electoral Vote
  •  
     
    This
    State
    National
    State
    National
    Monte Carlo
    Simulation

    Update
    Poll
    5-Poll
    2-party
    2-party
    Expected

    9/20/2008
    Aggregate
    Average
    Projection
    Projection
    Electoral Vote

    Obama
    McCain
     46.62 (50.36) 
     45.95 (49.64) 
     48.20 (51.83) 
     44.80 (48.17) 
    51.08
    48.92
    52.40
    47.60
    323
    215


        

    15-Poll

    End

    Sample

    Poll
    NATIONAL MODEL
     
    Pre  UVA
    5-Poll Mov Avg
     
    2-Party Projection  (60% UVA)
    5-Poll Mov Avg

    Trend
                                
    Rasmussen
    Gallup
    Hotline/FD
    Quinnipiac
    CBS/NYT

    Zogby
    Ipsos
    Pew Research
    Newsweek
    AP/gFk

    FOX News
    NBC/WSJ
    CBS/NYT
    CNN
    ABC/WP

    Registered V
    vs     Likely V
    Poll Averages

    Date
                
    9/19
    9/19
    9/18
    9/16
    9/16

    9/15
    9/15
    9/14
    9/11
    9/10

    9/09
    9/08
    9/07
    9/07
    9/07

    Size   
                  
    3000 LV
    2796 RV
    915 RV
    987 LV
    800 LV

    1008 LV
    1046 RV
    2307 LV
    1038 RV
    812 RV

    900 RV
    1000 RV
    655 RV
    942 RV
    1000 LV

    RV avg
    LV avg
    Total
    MoE
             
    1.79%
    1.85%
    3.24%
    3.12%
    3.46%

    3.09%
    3.03%
    2.04%
    3.04%
    3.44%

    3.27%
    3.10%
    3.83%
    3.19%
    3.10%
    Obama
                
    48
    50
    45
    49
    49

    47
    45
    46
    46
    44

    42
    46
    44
    48
    47

    45.6
    47.7
    46.4
    McCain
                
    47
    44
    44
    45
    44

    45
    45
    46
    46
    48

    45
    45
    46
    48
    49

    45.7
    46.0
    45.8
    Other
                
    5
    6
    11
    6
    7

    8
    10
    8
    8
    8

    13
    9
    10
    4
    4

    8.8
    6.3
    7.8
    Spread
                
    1
    6
    1
    4
    5

    2
    0
    0
    0
    (4)

    (3)

    1
    (2)
    0
    (2)

    (0.1)

    1.7
    0.6
     
    Obama
                
    48.2
    48.0
    47.0
    47.2
    46.6

    45.6
    44.6
    44.8
    44.4
    44.8

    45.4
    45.0
    44.6
    45.0
    43.8
    McCain
                
    44.8
    44.4
    44.6
    45.0
    45.2

    46.0
    46.0
    46.0
    46.0
    46.4

    46.6
    46.6
    48.4
    47.2
    46.0
    Spread
                
    3.4
    3.6
    2.4
    2.2
    1.4

    (0.4)
    (1.4)
    (1.2)
    (1.6)
    (1.6)


    (1.2)
    (1.6)
    (3.8)
    (2.2)
    (2.2)
     
    Obama
                
    52.40
    52.6
    52.0
    51.9
    51.5

    50.6
    50.2
    50.3
    50.2
    50.1

    50.2
    50.0
    48.8
    49.7
    49.9
    McCain
                
    47.60
    47.4
    48.0
    48.1
    48.5

    49.4
    49.8
    49.7
    49.8
    49.9

    49.8
    50.0
    51.2
    50.3
    50.1
    Spread
                
    4.8
    5.1
    4.1
    3.8
    3.0

    1.3
    0.5
    0.6
    0.3
    0.2

    0.4
    0.1
    (2.4)
    (0.6)
    (0.2)
    Win Prob
                   
    99.6
    99.7
    89.1
    88.1
    80.5

    65.8
    56.2
    62.1
    54.1
    51.8

    54.8
    51.0
    27.0
    42.2
    48.0
     

     
    Obamas EV and Popular Vote Win Probability

    Assuming the election is held today, Obamas win probability as calculated by fivethirtyeight.com (71.5%) is not consistent with their projected 303235 EV.

    The Election Model uses a 5000-election trial Monte Carlo simulation. The model projects that if a fraud-free election is held today, Obama would win 323215 Electoral votes with 51.1% of the two-party vote. The EV win probability is a simple calculation: Obama won 4926 of 5000 simulated election trials; his win probability is therefore 98.5% (4926/5000). Its a snapshot which changes slightly every day.

    The model indicates that for the same 303-235 EV split, Obamas EV win probability is 92% (assuming he wins just 50% of the undecided vote). Since the probability calculations in both models are based on the latest state polls, there is obviously a difference in methodology between the models.

    The Election Model base case scenario assumes that Obama will win 60% of the undecided vote. And this is conservative, as he is presumed to be the challenger (McSame is running for the third Bush term).

    View the Election Model Electoral Vote Simulation Frequency chart. Note that 4926 (98.5%) of the 5000 simulated election trials are over 270 for Obama. Compare this result to the equivalent fivethirtyeight.com chart in which 28.5% of the trials which McCain won are in red, while the 71.5% Obama won are in blue. The chart should be 98.5% blue.

    Obama also leads the National projection model (based on the average of the latest 5 national polls) with 52.4% of the 2-party vote. Note that the national polls lead the state polls, so that we can expect a rise in Obamas expected EV and win probability. The national model also assumes that he will win 60% of the undecided vote. The probability that he will win the popular vote is over 98%.

    As of Sept.20, electoral-vote.com has Obama leading by 273265; realclearpolitics has him losing by 202216 (120 tossup); fivethirtyeight.com has Obama by 303235. But the 2008 Election Model (EM) had Obama leading: 323215. Why the difference?

    Why Election Model projections differ from the Media, Academia and the Bloggers

    There are a variety of election forecasting models used in academia, the media and internet election sites. The corporate MSM (CNN, MSNBC, FOX, CBS, etc.) sponsors national polls to track the horserace and state polls to calculate the electoral vote.

    And why dont they mention the fraud factor? If just 2% of votes cast are uncounted (2.74% were in 2004) and 4% of Obamas votes are switched electronically to McCain, McCain will win by 293245 EV with 51.2% of the two-party vote.

    The EM uses Monte Carlo (MC) simulation method to calculate the probability of winning the electoral vote. Monte Carlo is widely used to analyze diverse risk-based models when an analytical solution is impractical or impossible. The EM is updated weekly based on the latest state and national polls. The model projects the popular and electoral vote, assuming both clean and fraudulent election scenarios. The EM allocates the electoral vote based on the state win probability in calculating a more realistic total Expected EV.

    Corporate MSM pollsters and media pundits use state and national polling data. Electoral vote projections are misleading, since they are calculated based on the latest state polls regardless of the spread; the state poll leader gets all of its electoral votes. This is statistically incorrect; they do not consider state win probabilities. And there is no adjustment for the allocation of undecided voters.

    For example, assume that McCain leads by 5149% in each of five states with a total of 100 electoral votes. Most models would simply assign the 100 EV to McCain. But that is an oversimplification: Obama could easily win one or more of the states, since his win probability is 31% :

    • The state projected vote share V(i) is the state poll share PS(i) plus the undecided voter allocation UVA(i):

      V(i) = PS(i)+UVA(i),   for i=1,51 states

      For this example, a final Obama projected vote share V(i) = .49 for all states is assumed (with distinct state poll shares PS(i) and respective undecided voter allocations UVA(i) implied). Five states total 100 EV.


    • The probability P(i) of winning each state assuming a 4% polling MoE (95% confidence):

      P(i)  =  NORMDIST ( V(i),  0.5,  .04/1.96,  true )

      .31 = NORMDIST( .49,  0.5,  .04/1.96,  true)  for each of the 5 states       (the NORMDIST function is available in Excel)

      The 2008 Election Model would allocate 31% of 100 EV to Obama and 69% of 100 EV to McCain.

    Bloggers also track state and national polls and do not adjust for undecided voters. A few use Monte Carlo simulation, but the EV win probabilities and frequency distributions are NOT consistent with the polling data. Either the state win probabilities and/or the simulation algorithm is incorrect.

    Academic regression models predict the popular vote but are run months prior to the election. They are typically based on economic and political factors rather than state or national polling data. They do not project the electoral vote. In 2004, virtually all of them forecast Bush to win by 5-10%. But since the election was stolen, the models had to be wrong they didnt factor election fraud as an independent variable in the regression. In fact, they never even mentioned the F-word in describing their methodologies.

    Fixing the polls: Party ID, Voted in 2000, RV vs. LV

    There has been much discussion regarding the recent McCain surge in the national polls. Most national and state polls are sponsored by the corporate MSM. Gallup, Rasmussen and other national polls recently increased the Republican Party ID percentage weighting. This had the immediate effect of boosting McCains poll numbers. But there are 11 million more registered Democrats than registered Republicans. USA Today/Gallup changed the poll method from RV to LV right after the Republican convention. Party-ID weights were manipulated to favor McCain as well.

    There is a consistent discrepancy between Registered Voter (RV) and Likely Voter (LV) Polls. The Democrats always do better in RV polls. No wonder: Since 1988, Democratic presidential candidates have won new voters by an average 14% margin.

    The manipulation of polling weights is nothing new. Recall that the 2004 and 2006 Final National Exit Polls weightings were adjusted to match the recorded vote miscount. But all category cross-tabs had to be changed, not just Party ID. Of course, the Final Exit Poll (state and national) is always matched to the Recorded vote, even though it may be fraudulent as it was in 2000, 2002, 2004 and 2006. This cannot be emphasized enough. Say it loud, again and again.

    In 2004, the 12:22am National Exit Poll (NEP) had a 3835 Democrat/Republican 'Party ID' mix.

    Kerry won  the 12:22am Preliminary NEP by 5148%.    ( 13,047 random sample, 1% MoE )

    The mix was changed to 3737 in the Final NEP  to 'force' a match to the Recorded vote;

    Bush won  the 1:25pm 'forced' Final NEP by 5148%.

    Likewise, the Gore/Bush 'Voted 2000' weights were changed from 3941 to 3743 in the Final    ('13047' & '13660' here).

    Bush was the official winner by 50.748.3% with 286 EV.

    The final 2004 Election Model projection indicated that Kerry would win 337201 EV with 51.8% of the 2-party vote.  In their Jan. 2005 report, exit pollsters Edison-Mitofsky provided the average exit poll discrepancy for each state based on 1250 total precincts. Kerry won the unadjusted aggregate state exit poll vote share by 52.047.0% (2-party 52.5%) with 337 electoral votes exactly matching the Election Model!

    In the 2006 midterms, the 7pm Preliminary NEP had a 3935 Democratic/Republican weighting mix. The Democrats won that NEP by 5543%. But the weights were changed to 3836 in the Final NEP in order to match the 5246% recorded vote; the Dem 12% margin was cut in half. Once again, the 'Voted 2004' weights were transformed: from Bush/Kerry 4745 at 7pm to 4943 in the Final. The landslide was denied; 10-20 Dem seats were stolen.

    The dead heat claimed by pollsters, bloggers and the media is a canard unless they are factoring fraud into their models and not telling us. The media desperately wants a horserace, and so they fail to adjust the polls for undecided and newly registered voters. They avoid McCains gaffes, flip-flops and plagiarisms, while he supports the most unpopular president in history.

    Polling data source:
    Electoral-vote.com
    RealClearPolitics.com


    THE 2008 ELECTION MODEL

    Last
    Aggregate
    5-poll
    2-party
    2-party
    Monte Carlo
    Simulation

    Update
    State
    National
    State
    National
    Expected

    9/20/2008
    Average
    Average
    Projection
    Projection
    Electoral Vote

     
     
     
    60% UVA
     
     

    Obama
    McCain
    46.62
    45.95
    48.20
    44.80
    51.08
    48.92
    52.40
    47.60
    323
    215


    2004 Final
     
     
    75% UVA
     
     

    Kerry
    Bush
    47.88
    46.89
    47.80
    46.60
    51.80
    48.20
    51.77
    48.23
    337
    201



    Sensitivity Analysis Impact of Uncounted and Switched Votes on Obama

    Uncounted
    1%
    2%
    3%

    Switched
    2%
    4%
    6%
    Vote%
    50.1
    49.0
    48.0
    EV
    292
    259
    226
    Vote%
    49.8
    48.8
    47.8
    EV
    276
    245
    212
    Vote%
    49.6
    48.5
    47.5
    EV
    261
    230
    199


    Sensitivity Analysis Impact of Aggregate State Projected Vote Share

    Undecided Voter Allocation Scenario
     
     
    Base Case

    Obama
    40%
    50%
    60%
    70%
    80%


    Projected 2-Party Vote Share

    Obama
    McCain
    49.6
    50.4
    50.3
    49.7
    51.08
    48.92
    52.2
    47.8
    52.6
    47.4


    MoE
    Obama Popular Vote Win Probability (Normdist)

    1.0 %
    2.0 %
    3.0 %
    21.4
    34.6
    39.6
    74.7
    63.0
    58.8
    98.3
    85.5
    76.0
    100.0
    98.4
    92.4
    100.0
    99.4
    95.3


    Obama Electoral Vote (Monte Carlo - 5000 election trials)

    Mean
    Median
    283.4
    283
    303.5
    303
    322.6
    324
    343.9
    345
    350.8
    353

    Maximum
    Minimum
    372
    176
    393
    223
    398
    236
    409
    262
    415
    278


    Obama Electoral Vote Win Probability (Monte Carlo)

    Trial Wins
    Probability
    3441
    68.8
    4577
    91.5
    4926
    98.50
    4998
    99.96
    5000
    100.0


    95% EV Confidence Interval
    Upper
    Lower
    335
    232
    352
    255
    368
    277
    384
    304
    389
    313


    States Won
    Obama
     
    23
     
    24
     
    27
     
    29
     
    29
     



    Full Update, with State Model:    http://www.democraticunderground.com/discuss/duboard.ph...

    If nominating, click here to recommend the full update above



     
    Refresh | +3 Recommendations Printer Friendly | Permalink | Reply | Top
     

    Home » Discuss » Topic Forums » Election Reform Donate to DU

    Powered by DCForum+ Version 1.1 Copyright 1997-2002 DCScripts.com
    Software has been extensively modified by the DU administrators


    Important Notices: By participating on this discussion board, visitors agree to abide by the rules outlined on our Rules page. Messages posted on the Democratic Underground Discussion Forums are the opinions of the individuals who post them, and do not necessarily represent the opinions of Democratic Underground, LLC.

    Home  |  Discussion Forums  |  Journals |  Store  |  Donate

    About DU  |  Contact Us  |  Privacy Policy

    Got a message for Democratic Underground? Click here to send us a message.

    © 2001 - 2011 Democratic Underground, LLC