Get PhotoCrank at PhotoCrank!
January 10, 2008

How Did The Polls Miss Hillary's Comeback?

Every poll taken in New Hampshire pointed to the same conclusion: Barack Obama would win, and win big. None of the polls released in the last week before the primary indicated that Hillary Clinton would edge Obama in the end, nor have a big comeback among women. Did she cry her way to the victory, or did every pollster somehow blow the Democratic race -- while nailing the Republican outcome?

The Washington Post thinks lachrymose:

What if the polls were right, and the dynamics changed dramatically on Election Day?....

One intriguing tidbit in the available data is that comparing exit-poll numbers with those from the last CNN-WMUR-University of New Hampshire poll shows a much bigger movement to Sen. Hillary Rodham Clinton (D-N.Y.) among women than among men. In the pre-election poll released Sunday, 34 percent of women said they supported Clinton, while the exit poll showed that 46 percent of women voted for the senator. The change among men was plus four percentage points.

Is this partial evidence of the "tear" effect that so many have latched onto? A return to the "gender gap" that polls showed before Iowa and the media storm that followed? As was clear last night, much more data analysis -- and more elections -- await.

One pollster brought up 1948, when polling services simply stopped surveys in early October because it seemed very clear that Thomas Dewey would beat Harry Truman. They did not capture the late-breaking movement towards the incumbent, and wound up with egg on their face. Another pollster states that this tosses "any shred" of their reputation for accuracy out the window.

Well, perhaps, but polls are tools, not clairvoyance. They measure very specifically a sample of people at a certain point in time, and it has its obvious limitations. The best poll is always the election; it has the largest sample and it's final. Everything else is guesswork, educated guesswork depending on the sample and the timing.

In this case, the polls and the methodology probably didn't cause the problem as much as the timing of developments in the race. Hillary's emotional outburst, such as it was, caught the media's attention and the imagination of New Hampshire voters. The swing in the female vote indicates it resonated among women. By the time it happened, almost all of the final survey calls had been made, and the pollsters had no chance to analyze its impact.

Don't blame the pollsters for last-moment developments. People don't stop paying attention to candidates after the pollsters stop calling. It's a reminder to everyone of the limitations of polling and the necessity of keeping attention fixed on the candidates themselves.


TrackBack URL for this entry:

Please note that unverified Disqus users will have comments held in moderation. Please visit Disqus to register and verify your account. Comments from verified users will appear immediately.