How did pollsters blow it in Clinton-Obama race?

MERRIMACK, N.H. — When politicians see polls they don't like, they recite a cliché: The only poll that counts is the one on Election Day.

Tuesday, the voters of New Hampshire proved the cliché right.

For days, poll after poll showed Illinois Sen. Barack Obama opening a big lead heading into the New Hampshire Democratic primary. But when the votes were counted, New York Sen. Hillary Rodham Clinton won. Even she seemed surprised.

Were the polls all wrong? Did the pollsters misjudge how many women would vote? Did voters lie when pollsters called? Or were the polls right about Obama leading, proving that debates and campaigning the last weekend really do matter and can sway voters at the last hour?

Regardless of the answers, many analysts urged a post-mortem to figure out what the heck happened in New Hampshire.

"It is simply unprecedented for so many polls to have been so wrong," said Gary Langer, the polling director for ABC News, in a memo posted at his Web site. "We need to know why."

Pollsters accurately predicted John McCain's comeback win in the GOP race. They nailed John Edwards' third-place finish among Democrats. But at least a dozen polls had the senator from Illinois defeating Clinton, almost all showing Obama gaining and opening a lead on Clinton.

Del Ali's Research 2000 poll turned out to be the most accurate overall in his surveys for the Concord Monitor, correctly predicting McCain's nearly 6-point victory and concluding that Obama was ahead of Clinton by just 1 point — with a 5-point margin of error.

A McClatchy-MSNBC poll conducted immediately before and after Iowa showed Obama with the support of 33 percent in New Hampshire, Clinton with 31. Polls conducted after Obama's Iowa win showed him with a bigger lead. One survey for C-SPAN and Reuters showed Obama up 42-29 percent over Clinton. Six public polls for news media and universities showed him with an average lead of 8.3 percentage points.

None showed Clinton close, let alone ahead. Yet she beat Obama by 39-36 percent.

So what happened?

One possibility widely mentioned Wednesday was that white New Hampshire voters with some bias might have lied to pollsters, expressing support for black Obama, then voting against him once they were in the privacy of the polling booth.

That's allegedly happened before — notably in the 1982 California election for governor in which Los Angeles Mayor Tom Bradley, who was black, was ahead in polls but lost the vote.

"There will be a lot of claims about what happened, about respondents who reputedly lied, about alleged difficulties polling in biracial contests," Langer said. "That may be so. It also may be a smoke screen, a convenient foil for pollsters who'd rather fault their respondents than own up to other possibilities — such as their own failings in sampling and 'likely voter' modeling."

Some pollsters said the record-shattering turnout may have produced a different electorate than the one envisioned in their models designed to predict who will vote. Others pointed to the surveys as voters left the polls showing that 17 percent made up their minds on primary day, which they said may have confounded the pre-election surveys.

"It's absolutely a cautionary tale to both the people who do polls and the people who read polls," said Richard Morin, a public-opinion expert at the Pew Research Center. "Pre-primary polling is fraught with dangers. That is particularly the case in New Hampshire, which I have called the graveyard of political pollsters."

Andy Smith, a pollster for the University of New Hampshire, noted that previous pre-election polls in New Hampshire have gotten the margins wrong, underestimating, for example, McCain's 18-point defeat of George W. Bush in the 2000 GOP primary.

It is clear that the timing of the polls missed a late surge of support for Clinton, particularly among women, influenced by a debate Saturday night, Sunday talk shows, round-the-clock campaigning and an emotional response from Clinton on Monday to the stress of the campaign.

"What the weekend polls found was an Obama lead as primary day approached," said Lee Miringoff, a political scientist and the director of the Marist Institute for Public Opinion at Marist College in New York, in an article on his Web site, www.maristpoll.marist.edu.

"What they do not reflect is what was apparent here in New Hampshire. The context of the campaign was changing. The last hours of the campaign were a media feeding frenzy over Clinton's show of emotion when responding to a voter's question on Monday morning."

Said pollster Peter Hart: "The problem with the polling performance in New Hampshire is exactly the same as it was some 60 years ago with the 'shocking win' election of Harry S. Truman. The pollsters concluded their polling before the voters made up their mind for the final time."

Democrat Truman defeated his Republican presidential challenger, Thomas Dewey, in 1948 and confounded the pollsters who had Dewey ahead before the election. A victorious Truman famously waved a copy of the Chicago Tribune with the inaccurate headline, "Dewey Defeats Truman."

Polls reflect public sentiment only at the time they're taken; they aren't predictions of a vote, even a few days later. Polls on different dates can yield different results.

In fact, Hank Parkinson, a Nashua contractor, said he'd waffled between the three leading Democratic candidates on primary morning.

"I heard John Edwards on the radio and was going to vote for him," said Parkinson, 44. "Then a Barack guy came by my house and I switched. Then my cleaning lady came over and said she voted for Hillary, so that's what I did, too."

Some pollsters push voters to pick candidates when they haven't made up their minds so as to arrive at a more complete prediction of the outcome, said David Moore, a former senior analyst with the Gallup Organization who now is affiliated with the University of New Hampshire.

"The pollsters don't want to say that 47 percent are undecided, and neither does the news media," said Moore, the author of "The Opinion Makers," a forthcoming book on polling.

All polls, of course, are just numbers. How they're read depends in large part on how the news media portray them. That's one reason that the National Council on Public Polls recommends that news media be cautious in interpreting polls.

Another thing to look for in polls is the margin of error.

In general, any number in a poll could be higher or lower by as much as the margin of error. It's a matter of statistical probability.

A number of bloggers Wednesday cited the "wildly inaccurate" polls as evidence that the vote was rigged.

"Other folks that I've spoken to, who follow this sort of thing, share my concern at this hour," wrote blogger Brad Friedman, a Los Angeles-based election-fraud watchdog, on bradblog.com.

"Something stinks in New Hampshire," a commenter posted on the popular liberal site Americablog.com.

Bloggers across the nation keyed into the fact that 81 percent of New Hampshire votes were being counted on machines that an HBO documentary alleged are easily hacked. It also didn't hurt that New Hampshire was the site of a recount after allegations of fraud in 2004, spotlighted in the much-praised documentary.

Compiled from McClatchy Newspapers, St. Louis Post-Dispatch, USA Today, The Dallas Morning News and Newsday.