Research 2000, Rasmussen, and the AR and PA primaries

Research 2000 very much wants you to know that they do polls for newspapers in St. Louis, Lexington, Fort Wayne, South Bend, and Reno. They don’t want you to think of them primarily as doing polls for left-wing activist outlets Daily Kos and now Democracy for America, the group founded to continue the work of former Presidential candidate Howard Dean.

Someone should tell Daily Kos and Nate Silver this though, as they beat the wardrums against R2k competitor Rasmussen Reports, that R2k is trying to look less partisan, not more.

First, let’s look at this poll that R2k did for DfA. In apparently the first poll since the first round primary, which showed Lincoln with 45 to Halter’s 43, Halter leads the poll 48-46 (MoE 5). In my model that shows a 58% chance that Halter leads, making this a near tie.

But that’s not really the story here. The story, to me, is that right as Research 2000 gets yet another race wrong, the attacks on Rasmussen (who got it right) commence. And I do mean another race wrong for R2k:

• McDonnell leads by 10! (no, actually it was 17)
• Daggett at 14! And Christie by 1! (no, Daggett got only 6 and Christie won by 4).
• Sestak +2! (Off by 6, while Rasmussen was only off by 3 with Sestak +5)
• And back to the race we started at, Lincoln by 9! (no, Lincoln beat Halter by 2)

About the only thing we can say about Research 2000’s polling is that it seems to get the winners right, but that’s not particularly useful. Activists, politicians, and campaigns need trends and margins to make decisions.

Further, this newest Arkansas poll itself is not free of criticism. Mark Blumenthal suggests at National Journal this poll is “priming the vote,” that is, trying to influence the race by dummying up a poll to favor Halter and then hiding the methodology on how they get the results. Blumenthal’s criticisms are similar to mine of a Rasmussen poll about Ron Paul. My theory about that poll was that the unnamed individuals who commissioned the poll rigged it just as Blumenthal suggests DfA rigged its poll.

So given the questions surrounding the Research 2000 polls, and this comparison with Rasmussen Reports, I eagerly await when Markos Moulitsas and Nate Silver demand that Research 2000 open its secret sauce to explain why they keep getting it wrong, as they demand Rasmussen Reports reveal its technique.