General Discussion
Related: Editorials & Other Articles, Issue Forums, Alliance Forums, Region ForumsNate Silver: Michigan is NOT a toss-up
In this update, Im going to focus on the polling weve seen in one particular state, Michigan, where there is an exceptionally wide spread between firms showing relatively strong numbers for Barack Obama, and those which have good numbers for Mitt Romney instead.
The national polling firms, like Rasmussen Reports, Public Policy Polling, and Marist College, show Mr. Obama ahead by an average of seven points in Michigan. By contrast, the Michigan-only pollsters show him ahead by only two points.
The advantage of the national pollsters is that we have a good sense for how to interpret their results. Some are Democratic-leaning and some are Republican-leaning but whatever house effect they tend to show, it is usually fairly consistent from state to state.
The head of Mitchell Research, Steve Mitchell, wrote a long memo accompanying his poll release on Monday. In that poll, he weighted the survey to assume that African-Americans would make up only 8 percent of Michigans turnout. By contrast, black voters represented 12 percent of the turnout in Michigan in 2008 according to exit polls, and 14 percent according to another source, the Current Population Survey. Blacks also made up 13 percent of Michigans vote in 2004 and 11 percent in 2000, according to exit polls. African-American participation is sometimes lower in midterm election years, but blacks were 12 percent of Michigans electorate in 2006, the exit poll reported that year. (There was no exit polling in Michigan in 2010.)
http://fivethirtyeight.blogs.nytimes.com/
JaneQPublic
(7,113 posts)...to earn lead status in a state than for Romney.
They should establish the exact number of points a candidate needs to lead in a "poll of polls" before being awarded lead status in a previously identified toss-up state and apply that standard to all states.
MrScorpio
(73,631 posts)We always have to clear a higher bar, while they're stepping over theirs.
It's the old double standard.
jeff47
(26,549 posts)The pollsters are producing results of "likely voters" - the mix of people who they think will show up on election day.
If you decide that 8% of the voters will be African-American, then Romney does better.
If you decide that 12% of the voters will be African-American, than Obama does better.
So the pollster can manipulate the result of the poll by manipulating their model of who's gonna show up. So even if you make some hard-and-fast line for "lead status", the pollsters can still tweak the results.
The conspiracy theory about Rassmusen is they start with a Republican-favored model, and then tweak the model towards reality when it gets close to the election. That way they look like they "got it right" by being close to the election results, but they can give Republicans a big perception boost in the months leading up to the election. Since they don't release the relevant data to refute this, I have no idea if it's true or not.
JaneQPublic
(7,113 posts)Thanks for sharing your knowledge and insight.
NashvilleLefty
(811 posts)several years ago that they weighted towards Republicans - their justification was that there are more Republicans than Democrats.
Ever since that admission, I would look at their polls and adjust it by 5 points in favor of the Democratic candidate and it almost always matched the average of other polls.
And remember this: in the 2004 election Rasmussen was the only pollster that was close to the results - despite the many reported problems with that election (read "stolen" .