TruthIsAll
10-30-2008, 07:31 AM
Professionals and university students agree with the 2008 Election Model:
http://www.geocities.com/electionmodel/2008ElectionModel.htm
Obama has a 100% probability of winning the election - not 90%, not 95%, but 100% - if ALL the votes are counted accurately and there is ZERO fraud.
Datawise Consulting
http://www.datawise-consulting.com/election.pdf
This report takes the latest poll data from each state and simulates possible outcomes of the national presidential election. The simulation takes into account the polling uncertainty and is repeated 10000 times to calculate an approximate probability of any particular outcome for the electoral college. This methodology is referred to as Monte Carlo simulation and is a well established methodology for analysing complex probabilistic problems. Below is the definition of Monte Carlo simulation from wikipedia.com.
"Monte Carlo methods are a class of computational algorithms that rely on repeated random sampling to compute their results. Monte Carlo methods are often used when simulating physical and mathematical systems. Because of their reliance on repeated computation and random or pseudo-random numbers, Monte Carlo methods are most suited to calculation by a computer. Monte Carlo methods tend to be used when it is infeasible or impossible to compute an exact result with a deterministic algorithm."
Introduction
The state by state polling data is collected from:
http://www.usaelectionpolls.com/2008/state-polls.html.
For simplicity it is assumed that all the polls have a standard sampling error of +/- 4% which is fairly typical for presidential polls. The data used for the analysis is shown in Appendix A, and was downloaded from usaelectionpolls.com on Oct 25, 2008.
Results
Running a Monte Carlo simulation based on the poll data available on Oct 25, 2008 (Appendix A) results in the following probabilities:
ˆ The probability for an Obama win is 100%.
ˆ The probability for a McCain win is 0%.
ˆ The probability for a tie is 0%.
Figure 1 shows a histogram of the probability for any particular electoral college outcome. The mode (the most likely result) is for Obama to get 378 electoral votes and for McCain to get 160 electoral votes. The probability for this outcome is 6.4%.
DeSart and Holbrook
http://research.uvsc.edu/DeSart/forecasting/
The latest run (Oct. 16) predicts that Barack Obama will win the election with 52.85%* of the national 2-party popular vote to to John McCain's 47.15%. The model also predicts that Obama will win the presidency with 354 electoral votes to McCain's 184. Based on these results, they calculate a 99.99% probability that Barack Obama will win the election.
University of Illinois
http://election08.cs.uiuc.edu/
This web site has been developed by computer science and political science students. It determined a 100% Obama win probability.
Other electoral vote forecasting models
http://www.google.com/search?num=100&hl=en&rls=GGLD,GGLD:2003-52,GGLD:en&q=electoral+vote+forecasting+models
270towin
An interactive site which runs 1000 Monte Carlo election trials. It also calculates a 100% Obama win probability.
http://www.270towin.com/simulation/
Franklin & Marshall College
Brian Adams, a mathematics and computer science professor, reports that there's a 99.98% chance that Sen. Barack Obama will win the presidential election on Tuesday. But his 50 million election trials were overkill. Only 5000 are necessary.
http://politicalwire.com/archives/2008/10/31/simulation_shows_obama_will_win.html
http://www.geocities.com/electionmodel/2008ElectionModel.htm
Obama has a 100% probability of winning the election - not 90%, not 95%, but 100% - if ALL the votes are counted accurately and there is ZERO fraud.
Datawise Consulting
http://www.datawise-consulting.com/election.pdf
This report takes the latest poll data from each state and simulates possible outcomes of the national presidential election. The simulation takes into account the polling uncertainty and is repeated 10000 times to calculate an approximate probability of any particular outcome for the electoral college. This methodology is referred to as Monte Carlo simulation and is a well established methodology for analysing complex probabilistic problems. Below is the definition of Monte Carlo simulation from wikipedia.com.
"Monte Carlo methods are a class of computational algorithms that rely on repeated random sampling to compute their results. Monte Carlo methods are often used when simulating physical and mathematical systems. Because of their reliance on repeated computation and random or pseudo-random numbers, Monte Carlo methods are most suited to calculation by a computer. Monte Carlo methods tend to be used when it is infeasible or impossible to compute an exact result with a deterministic algorithm."
Introduction
The state by state polling data is collected from:
http://www.usaelectionpolls.com/2008/state-polls.html.
For simplicity it is assumed that all the polls have a standard sampling error of +/- 4% which is fairly typical for presidential polls. The data used for the analysis is shown in Appendix A, and was downloaded from usaelectionpolls.com on Oct 25, 2008.
Results
Running a Monte Carlo simulation based on the poll data available on Oct 25, 2008 (Appendix A) results in the following probabilities:
ˆ The probability for an Obama win is 100%.
ˆ The probability for a McCain win is 0%.
ˆ The probability for a tie is 0%.
Figure 1 shows a histogram of the probability for any particular electoral college outcome. The mode (the most likely result) is for Obama to get 378 electoral votes and for McCain to get 160 electoral votes. The probability for this outcome is 6.4%.
DeSart and Holbrook
http://research.uvsc.edu/DeSart/forecasting/
The latest run (Oct. 16) predicts that Barack Obama will win the election with 52.85%* of the national 2-party popular vote to to John McCain's 47.15%. The model also predicts that Obama will win the presidency with 354 electoral votes to McCain's 184. Based on these results, they calculate a 99.99% probability that Barack Obama will win the election.
University of Illinois
http://election08.cs.uiuc.edu/
This web site has been developed by computer science and political science students. It determined a 100% Obama win probability.
Other electoral vote forecasting models
http://www.google.com/search?num=100&hl=en&rls=GGLD,GGLD:2003-52,GGLD:en&q=electoral+vote+forecasting+models
270towin
An interactive site which runs 1000 Monte Carlo election trials. It also calculates a 100% Obama win probability.
http://www.270towin.com/simulation/
Franklin & Marshall College
Brian Adams, a mathematics and computer science professor, reports that there's a 99.98% chance that Sen. Barack Obama will win the presidential election on Tuesday. But his 50 million election trials were overkill. Only 5000 are necessary.
http://politicalwire.com/archives/2008/10/31/simulation_shows_obama_will_win.html