There are many ways to keep score on whether Barack Obama or Mitt Romney has better odds of winning the general election, which is almost exactly six months away. Here at The Signal, we are fervent evangelists of the political prediction markets, where people place real money on the line to bet on the winner. These markets proved to be more prescient than polls in the Republican primary.
Many journalists prefer to stick to reporting on raw daily polls. While these surveys offer valuable information, it is dangerous to read too much into the daily fluctuations, especially this far in advance. Currently, Rasmussen has Romney leading Obama 49 to 44, while Rueters/Ipsos has Obama leading Romney 49 to 42. This disagreement is due to several common sources of error that occur on any poll. Averaging several polls to get an aggregate figure, as RealClearPolitics does, helps ameliorate these errors.
Upcoming work by Bob Erikson of Columbia and Chris Wlezien of Temple, recently presented at the Midwest Political Science Association conference, demonstrates a second problem with following the daily polls too closely. The researchers looked through past presidential elections, aggregated the national polls, and created the most effective forecast based on that data. They found that, even when properly aggregated and averaged, national polls do not have predictive power at this point in the cycle.