Sunday, January 10, 2010

COAKLEY WILL WIN, AND NOW I UNDERSTAND THE POLLING

A Boston Globe/University of New Hampshire Survey Center poll has Democrat Martha Coakley up by 15 in the Massachusetts Senate race, while Public Policy Polling, a Democratic-leaning firm, has Republican/teabag hero Scott Brown up by 1. An earlier Rasmussen poll showed Coakley with a single-digit lead. I'm looking at Mark Blumenthal's analysis at Pollster.com and I think I've found a good reason to doubt the PPP poll:

Consider the differences in the table below from within Globe/UNH and Rasmussen surveys. Both show a dead even race among the most interested and certain voters, while Coakley leads by huge double-digit margins among all other voters.



Those differences mean the overall results reported by any poll are going to be very sensitive to the "tightness" of the screen or likely voter model used. The more restrictive the screen, the closer the result. My assumption is that the "if you do not intend to vote...please hang up" automated methodology employed by PPP produced an effectively tighter screen and, thus, a likely voter sample closer to the "certain" or "extremely interested" subgroups of the Boston Globe and Rasmussen polls.

That "if you do not intend to vote...please hang up" message in PPP's robocall polls explains another shocking -- and spectacularly wrong -- poll result from PPP: a prediction that Doug Hoffman would win NY-23 by 16 or 17 points.

Look, what's going on in politics right now? Teabag types are ready to crawl naked through ground glass to vote for their heroes. So in polls like PPP's they're overrepresented, because they absolutely know they intend to vote.

But the average voter in Massachusetts? That voter probably thinks, "Hey, I don't know. I may be busy that day. Or the weather could be miserable. Or I could drop dead between now and then." Because that's what non-wingnuts are like. They don't live and die for politics. (This would be a better country if more of them did.)

But the percentage of non-wingnuts in the Massachusetts electorate is simply overwhelming. Even a modest turnout by them will probably crush Brown. And that, I think, is what we're going to see on January 19 -- a non-passionate Democratic and Democrat-leaning electorate turning out in middling numbers, but enough to defat Brown handily. Because lots of people who wouldn't crawl through ground glass to vote do wind up voting.

(The same thing, I imagine, happened in NY-23: it seems to be full of non-wingnut moderates, who are also lacking in the wingers' current intensity, but enough of them turned out to beat Hoffman.)

No comments: