Since lefthalfback upbraided me for not writing on the new NYT-Quinnipiac polls yesterday, and since I desire his approbation in all matters except the universal mandate, I hereby weigh in.
I was, frankly, a little suspicious of the numbers myself yesterday. Those results showed big Obama margins in three key states: He's up 51-45 in Florida, 50-44 in Ohio, and 53-42 in Pennsylvania. The twitters were full yesterday morning of conservatives debunking the methodology, and I felt they were actually making some decent points.
Today, conservative Hugh Hewitt posted an interview with a fellow from Quinnipiac named Peter Brown, presumably not the Peter Brown mentioned in "The Ballad of John & Yoko" (I actually met him once), and ask him some questions about the methodology.
The key conservative complaint is that the poll found far more Democrats than Republicans, and so the numbers are based on skewed samples. Brown explains that the company did its usual screening and reached its random scientific sample by the usual means, means it's always used. Then, it asked the people called what party they considered themselves to be members of:
HH: What’s the reasoning behind those models?
PB: Well, what is important to understand is that the way Quinnipiac and most other major polls do their sampling is we do not wait [sic, I'm pretty certain; this is supposed to be "weight," as in, adjust after the fact] for party ID. We ask voters, or the people we interview, do they consider themselves a Democrat, a Republican, an independent or a member of a minor party. And that’s different than asking them what their party registration is. What you’re comparing it to is party registration. In other words, when someone starts as a voter, they have the opportunity of, in most states, of being a Republican, a Democrat, or a member of a minor party or unaffiliated.
PB: So what’s important to understand is what we are doing is we’re asking voters what they consider themselves when we interview them, which was in the last week.
Okay, that sounds reasonable. But then Hewitt asks Brown if it passes the simple smell test:
HH: Do you expect Democrats, this is a different question, do you, Peter Brown, expect Democrats to have a nine point registration advantage when the polls close on November 6th in Florida?
PB: Well, first, you don’t mean registration.
HH: I mean, yeah, turnout.
PB: Do I think…I think it is probably unlikely.
HH: And so what value is this poll if in fact it doesn’t weight for the turnout that’s going to be approximated?
PB: Well, you’ll have to judge that. I mean, you know, our record is very good. You know, we do independent polling. We use random digit dial. We use human beings to make our calls. We call cell phones as well as land lines. We follow the protocol that is the professional standard.
So that's kind of a dodge. So I am frankly not sure that I trust those margins. However, I do think Pennsy is leaning strongly toward Obama these days. As of today, Nate Silver puts the probability of Obama winning the state at 86.7 percent. As a point of comparison, he has Montana at 85.2 percent for Romney, so he says it's slightly easier to imagine Obama winning Montana than Romney winning Pennsylvania.
I think Obama leads in those states, but not by those margins. Mr. Brown could argue, well, a poll is a snapshot, and we aren't saying what's true on August 1 is going to be true on Nov. 6. And that's perfectly respectable. But it's not about November.