Inaccurate State Polls, Continued

by Mike on October 23, 2008

in Election 2008,Media Bias,Politics

A few days ago, I posted on a number of inaccurate state polls coming out of Pennsylvania and Virginia. The poll samples in question showed Obama leading both states by double digits, but contained a far greater percentage of Democrats than historically showed up on election day, even in elections that Democrats won by landslides.

Some point to the Democrat party registration advantages in various states to justify this year’s oversampling, but that misses the mark. Every recent election features stories of increased Demcorat voter registration and Democrats have essentially held a registration advantage since the days of FDR. That advantage rarely if ever pans out on election day. The most scientifically valid way of measuring an election’s dynamic is to use a methodology that tracks prior elections. If it wasn’t, then there would be no such thing as a realignment because they would happen all the time.

Two days ago, I showed that something was off in Virginia and Pennsylvania. I was reassured when the most reliable state polling outfit confirmed my suspicions about Virginia. I was even more reassured by DJ Drummond’s analysis of this year’s polling from battleground states. The following is his chart of the difference between the party ID of voters in 2006 and the party ID of voters surveyed by Survey USA:

Pennsylvania: D+5 in 2006, SUSA using D+19, 15 point variance
Indiana: R+14 in 2006, SUSA using R+1, 13 point variance
Nevada: R+7 in 2006, SUSA using D+6, 13 point variance
Colorado: R+3 in 2006, SUSA using D+9, 12 point variance
Iowa: R+2 in 2006, SUSA using D+10, 12 point variance
Virginia: R+3 in 2006, SUSA using D+9, 12 point variance
Ohio: D+3 in 2006, SUSA using D+13, 10 point variance
Missouri: R+1 in 2006, SUSA using D+7, 8 point variance
North Carolina: R+1 in 2006, SUSA using D+5, 6 point variance

Something isn’t right. Again, DJ Drummond:

I’ve looked at the publicly available records on historical election participation, 2008 new voter registrations, and the Census information on these states, but I can find no valid reason for such large and arbitrary changes in political affiliation weightings. I would therefore submit that the models being used for many of the state polls have design flaws, which threaten the credibility of their published results.

That’s one way of putting it, though I agree with Kellyanne Conway (always Fitzpatrick to us). The pollsters are using junk science to move, not reflect public opinion.

Leave a Comment

You can use these HTML tags and attributes: <a href="" title=""> <abbr title=""> <acronym title=""> <b> <blockquote cite=""> <cite> <code> <del datetime=""> <em> <i> <q cite=""> <strike> <strong>

Previous post:

Next post: