CELL PHONE UPDATE....A new Pew study confirms something that Nate Silver wrote about a couple of days ago: We've finally gotten to the point where there's a serious cell phone bias in political polling:
The Pew Research Center for the People & the Press has conducted three major election surveys with both cell phone and landline samples since the conclusion of the primaries....A virtually identical pattern is seen across all three surveys: In each case, including cell phone interviews resulted in slightly more support for Obama and slightly less for McCain, a consistent difference of two-to-three points in the margin.
Back in 2004 the cell phone effect wasn't big enough to worry about, but cell phone penetration has continued to build, and now it is. A 2-3 point margin is pretty significant in an election cycle where the two candidates have rarely been more than five points apart.
At this point, I think political polls probably ought to routinely disclose whether they include cell phones in their calling samples. If they don't, they should be assumed to be at least moderately inaccurate. They can probably fix part of the problem by overweighting young people in their landline sample, but that's an iffy workaround. It's true that cell phone polling is more expensive since it has to be done by human beings, but I'm afraid that's going to be the price of entry for serious pollsters in the future.
And if that means fewer polls? Consider it a feature, not a bug.