I know I am an unknown and anonymous blogger whose mathematical skills can easily be questioned, but it is just strange to see how slow some light bulbs are turning on in the news media. As I noted last night, the poll confusion is not confusing at all.  There are two families of polls out there and every poll in each family is producing very similar results. So when I read some journalism major struggling to understand (let alone report on) what is happening it is very humorous:

Accuracy Of Polls a Question In Itself
Skeptics Challenge Assumptions Made

Could the polls be wrong?

…

Still, there appears to be an undercurrent of worry among some polling professionals and academics. One reason is the wide variation in Obama leads: Just yesterday, an array of polls showed the Democrat leading by as little as two points and as much as 15 points. The latest Washington Post-ABC News tracking poll showed the race holding steady, with Obama enjoying a lead of 52 percent to 45 percent among likely voters.

Emphasis mine because I want to answer the question for this poor lost journalist. The answer is one family of polls is absolutely wrong. Look at last night’s Bi-Poller Report to see where the two families lie in terms of results. The ‘extended’ (meaning overly optimistic) polls show an Obama lead of 9.2% (if you add in all the extended polls, not just the extended daily tracking polls). 15% is definitely closer to to 9.2 than it is to 2.0 percent! The ABC/WaPo poll’s 7% and is right in line with the extended poll range of 6.3-9.2%.  That is the family of polls their poll belongs in – the scientifically unproven family.

The Gallup ‘traditional’ poll of +2% is right in line with its family of polls which last night averaged 4%. This group has been scientifically validated through decades of use in elections. When grouped by their statistical bimodal results, it is easy to discern why a poll falls into one family of results – their turnout models.  The traditional polls use historic voting models to produce their results. The ‘extended’ use some new, fuzzy math.

Now some cold water for the McCain-Palin side. The only way for the ‘extended’ polls to be right is for people on the McCain-Palin side to not get out to vote (and drag 2-5 friends with them). As I noted last night McCain’s internal polls show the wave of interest in this election is historically high – which means both McCain and Obama supporters are coming out in large numbers. If McCain-Palin do generate enough enthusiasm to match Obama-Biden (pullease – two senators??) then the ‘traditional’ polls will be the ones which accurately predicted the outcome.

The cold water is the fact that Democrat Primary voters outnumbered the GOP voters by 2-to-1 this spring. This was before Palin and with a fractured and listless GOP base. My feeling is, and what I see on the streets and in the debate audiences and in the stump speech crowds, there is more than enough enthusiasm on the right to trash those ‘extended’ polls and their “Dewey Wins!” foolishness. But what I think doesn’t matter. What you folks do is the only thing that counts.

Tags: 2008 Election, Extended, Polls, Traditional