I know a lot of folks are poll junkies here. I am. That’s not a bad thing except when we set our emotional state to the presidential polls. Quick quiz: can you name exactly what time RAND, Rasmussen, and Gallup release their daily tracking polls? If you can answer 1 am Pacific time, 630 am Pacific time, and 10 am Pacific time, then you are a poll addict.
And if you’ve been watching the polls, you’ve seen that the national daily tracking polls are moving toward President Obama in the past few days. We can see this in PPP, Reuters, IBD. Even Gallup moved a tick.
But not Rasmussen. Now I know why.
Mark Blumenthal of pollster.com highlights in a piece how Rasmussen has made an important shift in its partisan weighting that makes it look like Republicans and Romney are doing better than they were just a week ago. It ain’t true. Join me after the jump to learn why.
In analyzing the Rasmussen numbers pre- and post-second Mitt presidential debate, Blumenthal notes that Rasmussen has shown an uptick toward Romney in its national and state polls. It’s an uptick that is out of line with other polls since the second debate. For example, It has Romney up by 1 today and its swing-state poll made a huge 4-point shift to Romney earlier this week.
I saw that and went hmmmm. But I needed Blumenthal’s piece to figure out why.
There is a catch, however. Rasmussen is one of the few pollsters to routinely weight its samples so they match predetermined targets for the percentage of likely voters that identify as Democrats or Republicans. The catch, as Rasmussen Reports confirms to The Huffington Post, is that its weighting targets are now adjusting on a weekly basis to match the average party identification for likely voters measured on their last six weeks of calling (after weighting for demographics, but not for party). So the party weights for the past recent week may be slightly different than the party weights the week before.
More important, the weight targets for Rasmussen's national samples grew slightly more Republican in mid-October. Although the data are published on pages available to paid subscribers only, Rasmussen indicates that the national interviews for the week of Oct. 8 to 14 gave Democrats a 1-point edge over Republicans (38 to 37 percent). The party balance for the two prior weeks, Oct. 1 to 7 and Sept. 24 to 30, was a 3-point Democratic advantage (39 to 36 percent).
... A 3-point shift toward a more Republican identification would more than explain the one-point shift to Romney in the five states Rasmussen surveyed this week.
Now, there are plenty of folks here at DK who are convinced that Rasmussen cooks it books to make Republicans look good. I don’t think it does. It’s not Research 2000.
But I am 100% certain that Rasmussen is not an enterprise that foregrounds its methodology, and it’s lack of transparency is on full display right now. This shift in partisan weighting is a HUGE deal, and it’s exactly the kind of thing poll junkies need to know about. A forthright pollster would tell everyone about this shift, not bury it in the fine print.
But more importantly, it means that the shifts in Ras’ data toward Romney are pushed along by a very large thumb on the scale.
As an fyi, conservatives like to make the case that they’re un-skewing polls. In this case, Ras is “adjusting” (i.e. skewing) the data on a weekly basis. Don’t let it skew your perspective.