Sunday, December 23, 2012
The 2012 elections were extensively regarded as win for pollsters and poll aggregators, and for good motive. Most of the polls at the end of the crusade, especially in the serious swing states, properly predict President Barack Obama as the winner.
But not everybody decided. "We spent a whole bunch of time," Obama campaign manager Jim Messina said after the voting, "figuring out that American polling is busted." Now that the vote count is almost absolute with all but two states, New York and Hawaii, having particular their election results the full story emerge to fall anywhere in between.
While the public polls together predicted an Obama victory, they also inconspicuous Obama's margins, both countrywide and in a half-dozen battlefield states. And, perhaps more prominently, some polls told very dissimilar stories about how much voter partiality shifted over the final weeks of the crusade.
On Tuesday, the National Council on Public Polls unrestricted its biennial report on polling precision. "Generally speaking, the national and state polls this year did okay," NCPP leader Evans Witt told The Huffington Post, though "they didn't come quite as close to corresponding the election consequences as they had, for example, in 2008."
The average error for final week approximation of sustain for each applicant as intended by NCPP was faintly higher in national polls this year (1.4 percentage points) than in 2008 (0.9), 2004 (0.9) or 2000 (1.1), but was lesser than in 1996 (2.1), 1984 (2.4) or 1980 (3.1).