The Most (and Least) Accurate Polls

As we head into the final stretch of the campaign, we're likely to be inundated by a spate of poll results from all kinds of different organizations, and if, well, everything is any indication, then different pollsters are likely to show very different things about the state of the race in key swing states. There may be no point in trying to make sense of mind-bogglingly contradictory survey results, but in case anyone is interested, I took a look at the polling done in the run-up to the 2010 midterms and constructed a little table on which pollsters came the closest to foretelling the election results in states that are now considered "battleground" territory and which missed the mark.

I measured polling accuracy by looking at the results of the last public poll of each race by each pollster and comparing the margin between the two highest-polling candidates (sometimes the only two candidates) to the eventual winner’s margin of victory over the second-place finisher. If there was more than one poll tied for most or least accurate by this metric, then I compared each candidate’s individual poll position in the survey results with their eventual share of the final vote. This is why PPP is listed as having the most accurate poll of the Florida governor’s race despite the fact that their final pre election poll had Alex Sink (D) leading Rick Scott (R), the eventual victor, 48% to 47%. This was rated "most accurate" notwithstanding Scott’s victory because it underestimated Scott’s eventual share of the vote (48.9%) by only 1.9 percentage points, while overestimating Sink’s vote share (47.7%) by only 0.3 points. The next-most accurate survey of this race was conducted by Rasmussen Reports, which had Scott leading by three points heading into Election Day.

Race	Most Accurate Poll	Least Accurate Poll
Ohio Gov.	Columbus Dispatch*	CNN/Time
Pennsylvania Gov.	Rasmussen Reports	Franklin & Marshall
Florida Gov.	PPP (D)	Suffolk University
Colorado Gov.	CNN/Time	Magellan Strategies (R)
Colorado Sen.	Denver Post/SurveyUSA	McClatchy/Marist
Florida Sen.	Rasmussen Reports	TCPalm.com/Zogby
Iowa Sen.	Des Moines Register	KCCI/Research 2000
Nevada Sen.	Suffolk University	Rasmussen Reports
New Hampshire Sen.	WMUR/UNH	ARG
North Carolina Sen.	PPP (D)	SurveyUSA
Ohio Sen.	PPP (D)*	Suffolk University
Pennsylvania Sen.	Susquehanna	McClatchy/Marist
Wisconsin Sen.	McClatchy/Marist Rasmussen Reports	PPP (D)
Wisconsin Gov.	McClatchy/Marist	Rasmussen Reports Reuters/Ipsos
Nevada Gov.	PPP (D) Suffolk University	CNN/Time
Iowa Gov.	KCCI/Research 2000	Rasmussen Reports
New Mexico Gov.	Daily Kos/PPP (D)	SurveyUSA
Michigan Gov.	EPIC-MRA	Rossman/Team TelCom
New Hampshire Gov.	WMUR/UNH	ARG

*Nailed it! (Poll results conformed exactly to election results.)

Of course, not all these races were as close as the presidential race is this year. The Senate races in Florida, Iowa and New Hampshire, and the gubernatorial elections in Colorado and Michigan, were all blowouts. Take that however you like. Also notice that the above table does not include any data from Virginia, which had neither a U.S. Senate race nor a gubernatorial election in 2010. In the 2009 race for governor there, SurveyUSA was right on the money; its final poll before Election Day showed Bob McDonnell (R) leading his Democratic opponent, Creigh Deeds, by eighteen points 58% to 40%. McDonnell won that election with 59% of the vote to 41% for Deeds. That was three years ago, however, so it may not be worth much.

Finally, there are a handful of states that are assuredly not up for grabs in the presidential election but are experiencing heated U.S. Senate and/or gubernatorial races. For those who are interested, here are my findings on polls of 2010 races in those states.

Race	Most Accurate Poll	Least Accurate Poll
Connecticut Governor	CT Capitol Report/MRG	Suffolk University*
U.S. Senate – Connecticut	PPP (D)	Rasmussen Reports
Maine­ Governor	PineTreePolitics/MECPO	Critical Insights
Massachusetts Governor	Suffolk/7News	Rasmussen Reports
U.S. Senate – Washington	FOX News/POR-Rasmussen	PPP (D)

Anything Can Happen

Let's start by acknowledging the inevitable: Mitt Romney will win the New Hampshire primary. I'll be stunned if he doesn't win by double digits. Having already placed first in the Iowa caucuses, Romney should have the nomination sewn up after a decisive win in New Hampshire, yet Pundits, pollsters and political junkies are buzzing about "the battle for second place" (as well as 3rd and 4th, if it's close). What I find especially interesting is that the air of mystery surrounding the first-in-the-nation primary this year is just as strong, if not more so, than it's been in previous years, despite Romney's incredibly strong poll position going into tonight and the paucity of doubt that he'll win by a sizeable margin. It's anyone's guess what order the runners-up will finish when all the N.H. votes are tallied. Ron Paul has consistently been polling in 2nd place since Newt Gingrich's collapse, but just like in Iowa, he seems to have plateaued. It's also worth noting that, while Santorum and Romney both outperformed their poll numbers in Iowa, Ron Paul's 21% of the vote was much closer to his position in the polls leading up to the caucuses. (A similar phenomenon occurred in 2008, where Romney and McCain both finished well ahead of their positions in the RCP average, while Paul underperformed.) For you empiricists out there, this portends and underwhelming finish for Paul in the Granite state, but he'll no doubt plod along.

The most exciting thing may be a last-minute surge by Jon Huntsman, who's arguably got the most to lose tonight (except for Mitt Romney). I pondered this possibility in a post last week, but by this weekend I was convinced that that ship had sailed. I may have spoken too soon; a spate of polls out of New Hampshire show real momentum for the even-tempered Mormon Sinophile. Rasmussen Reports has him at 15%, up from 12% in their previous New Hampshire survey. Public Policy Polling, which also had Huntsman polling at 12% the last week of December, released the results of a poll that pegged him at 16%. Perhaps most telling is the candidate's surge in the Suffolk University/7News tracking poll, in which Huntsman has doubled his share of the vote in the last week.

All of these polls have Huntsman in 3rd place, behind Romney and Paul, but a poll released over the weekend from American Research Group has him in 2nd place at 17%, followed by Ron Paul at 16%. Today the two are separated by three percentage points in the RCP average of N.H. polls, which for some reason does not include the ARG survey results; just five days ago, that gap was twelve points.

Huntsman won't win the New Hampshire primary, but there's a very real possibility that he could come in a strong 2nd. That would effectively quash Rick Santorum's momentum coming out of Iowa, and with a 10-day interim between today and the South Carolina primary, just about anything can happen.

Can Huntsman make a Santorum-style surge in New Hampshire?

The biggest story to come out of last night's Iowa caucuses last night--apart from Mitt Romney's unprecedented eight-vote margin of victory--has to be Rick Santorum's amazing (and, for most, unexpected) performance. The former Pennsylvania senator had been polling in the single digits in Iowa and barely registering nationally. Then, about a month ago, his poll numbers in the Hawkeye state began creeping up, and by last week, he was nipping at the heels of Ron Paul and Mitt Romney, who were locked in a virtual dead heat atop most surveys. In no poll did Santorum register more than 18% support, however, making the 25% of the vote he pulled in last night's caucuses all the more impressive.

Never taken seriously by the media and most primary voters, Santorum long ago decided to focus almost exclusively on Iowa, and he still had to stretch his miniscule campaign treasury pretty thin (as evidenced by the pickup truck he traveled the state in). He didn't have much, but he had a message--and an m.o. (Sorry for the alliteration; I can't help it.): visit every county; talk to anyone who will listen; speak from the heart; perform the occasional exorcism. (I might not have that exactly right, but I wasn't there. This is all being relayed secondhand.) It's a strategy reminiscent of Mike Huckabee's 2008 campaign, which peaked when the former Arkansas governor won the Iowa GOP caucuses, only to flame out like a supernova.

It's also strikingly similar to another candidate's strategy this year. Jon Hunstman, Jr., the former Utah governor and veteran diplomat, is trying in New Hampshire what Santorum tried (successfully) in Iowa. He's devoted more time to the state than anyone left in this race (which, as of this morning, does not include Michele Bachmann), but he still lags way behind Romney in the polls there. (Even worse, he hasn't even gained as much support in the state as Ron Paul.)

This is not to say that all of Huntsman's time and effort in the state has been for naught. As is so often the case, the numbers tell the tale: Eight weeks ago, Huntsman and Gingrich were tied in the RCP average of polls in New Hampshire. As Gingrich began to gain steam, he pulled away, and soon moved into a firm 2nd place behind Romney in the Granite State. One month later, the former Speaker peaked at 24.3% in the RCP average. (Romney was at an even 36%.) Huntsman, meanwhile, crept up to 11.8% by Christmas, by which time Gingrich was down to 20%. Since then, however, Huntsman hasn't gained much traction; he's actually down slightly, at 10.3% as of today. (Gingrich sits at 11.3% and will probably sink even further before next Tuesday's primary.)

Today, the media's primary focus shifts from Iowa to New Hampshire, and the results of a Suffolk Tracking poll did not provide welcome news for Huntsman, who I maintain is the best candidate we've got. He registered only 7% support in the survey of 500 "likely GOP primary voters," a distant 4th behind Romney, Paul and Gingrich. That's actually his worst showing in a New Hampshire poll in nearly two months. If Huntsman is hoping to pull off a Santorum-style surprise, then he's going in the wrong direction.

Huntsman's best argument against the plutonian picture painted by the polls (There's that alliteration again! Damn!) may be that all polls taken in the run-up to the Iowa caucuses greatly underestimated Santorum's performance there, by anywhere from seven to ten percentage points. He may also want to point out that, six days before the caucuses, Santorum was at 9.8% in the RCP average of polls there, half a point lower than Huntsman's current position in the New Hampshire poll average.

It's highly unlikely that anyone other than Mitt Romney will win the 2012 New Hampshire Republican primary, but there's still a very good chance that Jon Huntsman will finish a strong second. The days ahead will be critical; if no one even comes close to Romney in the polls and he wins the primary by double digits, then he'll be in very good position going into South Carolina, with a ten-day buffer to shore up his support there.

To the anybody-but-Romney crowd, I say: you've gone through everyone else; if you don't want to vote for Mitt, then your only choices are Santorum, Huntsman or Dr. Paul. (C'mon, do you really even need to think about this?)