Gallup has been doing polling since forever. (Okay, I know it hasn’t really been forever. It’s only been 70 years, but you get my point.) Gallup release the results of two polls yesterday. One was their daily tracking poll which I try not to look at because it has little or no meaning. We don’t elect our president as a nation, instead we elect by states. Therefore a tracking poll of each state would be of better value.
I took a look even though a national tracking poll is a popularity contest (or a horse race) which may have no reflection on how states will vote. Anyway, in the Daily Tracking poll Senator Barack Obama was up by eight points. In a separate Gallup poll, Obama was ahead among registered voters but behind Senator John McCain in the subgroup of likely registered voters by four points.
I listened to Countdown last night. Keith Olbermann and Richard Wolfe tried to make some sense of these numbers but they mangled it pretty badly. So, I went to one of my best sources for polling results, the blog 538. (See below the video for an excellent explanation.)
Kudos to Gallup for disclosing the process and perils of its likely voter model, but as Alan Abramowitz has noted at Pollster.com, something about the new USA Today/Gallup poll showing John McCain 4 points ahead among likely voters — but 3 points behind among registered voters — doesn’t quite sit right:
How do you get from a 47-44 Obama lead among RVs to a 49-45 McCain lead among LVs?
A few quick calculations shows how. You have 900 RVs and 791 LVs, so that means that among your 109 UVs (that’s unlikely voters according to Gallup) Obama leads McCain by a whopping 61% to 7%.
Putting it another way, according to Gallup 16% of registered Obama supporters are unlikely to vote compared with only 2% of registered McCain supporters.
Whatever one thinks about likely voter models in general, the mathematics of this particular implementation defy credulity. Although, we should probably wait for USA Today to release its crosstabs so we can make sure there wasn’t a typographical error of some kind in the write-up.
Also, this is a good time to mention Robert Erikson’s critique of the extra volatility introduced by Gallup’s likely voter model in past election cycles.