Thursday, October 28, 2010

Emmer camp disputes MPR poll, releases internal

Public Opinion Stratagies (10/28, likely voters, no trend lines):
Mark Dayton (D): 40
Tom Emmer (R): 40
Tom Horner (I): 13
Undecided: -
(MoE: ±4.38%)

In response to the release of the MPR/Humphrey Institute poll showing Tom Emmer down by 12 points to Mark Dayton, the Emmer campaign released an internal poll by POS conducted on October 24th and 25th that shows the race tied.

I'll let the infamous Cullen Sheehan take it from here:

All polls are snapshots in time. The new MPR/Humphrey Institute results are an unfortunately predictable snapshot in absurdity. The HHH poll's track record rivals only television weather forecasters for accuracy. Four years ago this same poll predicted that Mike Hatch would beat Tim Pawlenty by six percentage points. Minnesota should be as confident in this poll's prediction as Governor Hatch was during the last gubernatorial campaign.

Unlike many of you I'm not just going to dismiss this internal poll out of hand. I'm not going to include it in the GPI, because I'm not including internal polls, but that's not because I think it's made up or fake.

The reason internal polls are not included in the GPI is because we don't know anything about previous polls that the Emmer campaign, or the Dayton campaign, or the Horner campaign, has commissioned and what results they have shown. We don't have any context in which to put the poll.

Additionally internal polls tend to have a substantial bias in favor of the campaign that commissioned it. Again, I don't think this is because they are making things up or fudging the numbers, but think about it this way.

If you commission three polls, you're obviously going to release the one with the best numbers and not mention the other polls that didn't have such good results for you.

Here's Nate Silver explaining it much better:

I’m not sure why people take polls released by campaigns at face value. This does not mean that campaigns don’t have very good pollsters working for them. But the subset of polls which they release to the general public is another matter, and are almost always designed to drive media narrative. For an instructive example, Google the term “internal polls”: the first result is a blog post, circa late October 2008, entitled “McCain’s Internal Polls Looking VERY Good.”

What we’ve found is that is that polls commissioned by campaigns and released to the public show, on average, a result that is about 6 points points more favorable to their candidate’s standing than nonpartisan polls released at the same time. (Other analysts have found similar results.) So, just as a first cut, you might take a Democratic internal poll that shows a tied race and “translate” it into nonpartisan terms by adding 6 points to the Republican’s margin.

So you take that Emmer internal showing a tied race, subtract six points from it and you have Mark Dayton by six points. Six points, coincidentally enough, is exactly what the current GPI says Mark Dayton's lead is.

No comments:

Post a Comment