NYT's numbers guru Nate Silver today breaks down the results on the country's myriad pollsters and finds that Rasmussen -- oft-cited in this space -- was the worst out of the most frequent midterm election pollsters. We often identify Ras (which occasionally does polls commissioned by Fox News) as a right-leaning organization, and Silver confirms that the polls are often biased toward Republican candidates. Why? Take it away Mr. Five-Thirty-Eight.
Rasmussen, for instance, generally conducts all of its interviews during a single, 4-hour window; speaks with the first person it reaches on the phone rather than using a random selection process; does not call cellphones; does not call back respondents whom it misses initially; and uses a computer script rather than live interviewers to conduct its surveys. These are cost-saving measures which contribute to very low response rates and may lead to biased samples.
Rasmussen also weights their surveys based on preordained assumptions about the party identification of voters in each state, a relatively unusual practice that many polling firms consider dubious since party identification (unlike characteristics like age and gender) is often quite fluid.
The result: An average miss of 5.8 percent in an average of their final three weeks of polling vs. the actual vote count. In Pennsylvania, Ras actually did fairly well: Its final poll had Pat Toomey ahead in the Senate race by 4 points, and he won by 2. In the governor's race, it hit Tom Corbett's 9-point margin of victory on the money in its final poll.
So where did Ras screw up? Well, the Hawaii Senate race, for one, where they missed the final margin for Sen. Daniel Inouye by 40 FREAKING POINTS. Silver reports that this is "the largest error ever recorded in a general election in FiveThirtyEight’s database, which includes all polls conducted since 1998." But that one blunder wasn't enough to pull the results that far, since Rasmussen conducted a prolific 105 polls in the final three weeks before the election.
So who did well by Nate's calculations? Quinnipiac tops the list, seen above. Another interesting note, almost all of the top polls had a (typically small) Republican lean. Did nearly everyone underestimate Dem turnout this year? (Not that it helped them much.)