Dynamic Bayesian Forecasting of Presidential Elections in the States

I present a dynamic Bayesian forecasting model that enables early and accurate prediction of U.S. presidential election outcomes at the state level. The method systematically combines information from historical forecasting models in real time with results from the large number of state-level opinion surveys that are released publicly during the campaign. The result is a set of forecasts that are initially as good as the historical model, then gradually increase in accuracy as Election Day nears. I employ a hierarchical specification to overcome the limitation that not every state is polled on every day, allowing the model to borrow strength both across states and, through the use of random-walk priors, across time. The model also filters away day-to-day variation in the polls due to sampling error and national campaign effects, which enables daily tracking of voter preferences towards the presidential candidates at the state and national levels. Simulation techniques are used to estimate the candidates’ probability of winning each state and, consequently, a majority of votes in the Electoral College. I apply the model to pre-election polls from the 2008 presidential campaign and demonstrate that the victory of Barack Obama was never realistically in doubt. The model is currently ready to be deployed for forecasting the outcome of the 2012 presidential election. Acknowledgements: I am grateful to Cliff Carrubba, Tom Clark, Justin Esarey, and Andrew Gelman for feedback on earlier versions of this paper. Nigel Lo provided helpful research assistance. A special debt is owed to my colleague Alan Abramowitz, who could not have been more generous with his time, his insight, and his data.