6/13/2012
Written by
You could wade through months of rhetoric, third-party opinions, and fundraising reports, or, you could visit the Election Analytics website developed by Professor Sheldon H. Jacobson and his students.
As director of the Simulation & Optimization Lab in the Department of Computer Science, Jacobson is well-known for his work in Operations Research (OR). OR combines a multitude of tools in engineering, computer science, mathematical modeling and algorithms, and statistical analysis. It also utilizes tactics like probability theory, game theory, decision analysis, and simulation to find optimal solutions to complex problems.
OR’s countless applications have led Jacobson and his group to conduct research in areas as far-flung as aviation security, vaccine and immunization, public health, automobile fuel consumption, and NCAA basketball tournament brackets, as well as predictions for three previous presidential elections.
The mathematical model that successfully predicted the outcome of the 2008 Presidential Election employs Bayesian estimators that use available state poll results to determine the probability that each presidential candidate will win each of the states. These state-by-state probabilities are then used in a dynamic programming algorithm to determine a probability distribution for the number of Electoral College votes that each candidate will win in the 2012 presidential election.
For the 2012 elections, the Election Analytics Team has extended the model to handle both Senate and House races in addition to the Presidential race. In the case of the Senate and House races, the individual state probabilities are used to determine the number of seats that each party will control. New prediction results will be posted as new polling data is made available.