Tag Archives: presidential election polls

Watching the polls

Politics, , , , ,

Or more specifically, Nate Silver. The New York Times‘ resident stats wizard now has Barack Obama at an 85.1% chance of winning the election on Tuesday:

There are not really any recent precedents in which a candidate has led by something like 49 percent to 46 percent in the final polling average, as Mr. Obama does now in Ohio, and has wound up losing the state. That does not mean such misses cannot or will not occur: there have only been a few elections when we have had as much state polling data as we do now, which is why the model allows for the possibility of a 1980-type error based on how the national polls performed that year.

But the reasonably high level of confidence that the model expresses in Mr. Obama’s chances of winning Ohio and other states reflects the historical reality that the polling average normally does pretty well.

That brings us to Pennsylvania — where the forecast model puts Mr. Obama’s chances at better than 95 percent.

One poll of Pennsylvania on Saturday, from Susquehanna Polling and Research, showed a different result, with the two candidates tied at 47 percent. But in context, this is not such a great poll for Mr. Romney.

The polling firm has had a very strong Republican lean this cycle — about five percentage points relative to the consensus, a much larger lean than firms like Rasmussen Reports and Public Policy Polling that are often criticized for having partisan results. Susquehanna is the only pollster to have shown Mr. Romney ahead in Pennsylvania at any point in the race, as they did on one occasion in February and another in October (Mr. Romney led by four points in their previous poll of the state). Perhaps they will be proven right, but it is usually a bad bet to bank on the one poll rather than the many.

Still, Mr. Romney’s campaign is making a late play for Pennsylvania with advertising dollars and a visit there on Sunday.

That is probably a reasonable strategy, even though Mr. Romney’s chances of pulling out a victory in Pennsylvania are slim. What makes it reasonable is that Mr. Romney’s alternative paths to an Electoral College victory are not looking all that much stronger.

Nate Silver vs. the Mittmentum Mountaineers

Media, Politics, , , , , , , ,

As Election Day approaches and the nation continues to whip itself into a collective frenzy, there sometimes seems to be only one guy in all of our national media who hasn’t succumbed to the wild swing of emotions that has captured everyone else.

Nate Silver, of the New York Times‘ FiveThirtyEight blog, has been posting daily with updates from swing-state polls. And even while most of the media have gleefully jumped aboard the “momentum is shifting to Mitt Romney” train, Silver has calmly continued to insist on using real data, instead of relying on phantasmic predilections of victory based on rally turnouts in random Ohio towns. This latter course is essentially what national campaign reporters, always desperate for a more sensational story, have been doing, and it’s quite possible that the collective content of their coverage actually will help make the race closer. But if that happens, it will be due, ironically enough, to their own misreading (or woeful ignorance) of existing polls, not because they were right in the first place.

According to Silver, as of yesterday Barack Obama was leading in Colorado, Iowa, Nevada, New Hampshire, Ohio, Virginia, and Wisconsin. Mitt Romney, meanwhile, was leading in Florida and North Carolina. If the races end up exactly that way in the end (see interactive map here), Obama will win with 303 electoral votes to Mitt Romney’s 235, easily surpassing the requisite 270 to win reelection. In fact, Obama could even lose the three additional states in which Nate Silver’s model gives him the smallest leads: Colorado (58% probability of winning), Virginia (60%), and New Hampshire (70%). (Remember, these figures represent the likelihood that Obama will win these states, not the percentage he’s receiving in head-to-head polls. Example: Obama is expected to win 58% of the actual vote in Massachusetts, but Silver estimates his probability of winning the state at 100% because there is virtually no possibility that the polls will shift significantly enough before the election to cause him to lose there.) In other words, even if Romney took those three states — Colorado, Virginia, and New Hampshire — as well as Florida and North Carolina, the final electoral vote count would nevertheless give 277 to Obama and 261 to Romney, thereby granting the president a second term. The media may be intent on creating a wild photo-finish, but Silver’s analysis suggests Obama’s still in a fairly good spot.

Related articles

“Unskewed” polling?

Politics, , , , ,

In light of recent attempts by Republicans to soften the blow of polling showing a solid Obama lead (attempts which have been widely mocked), I highly recommend this very detailed analysis by Mark Blumenthal from three months ago on how polling methodologies differ, and why these differences are so crucial this election year:

As a Pew Research Center study recently demonstrated, random-sample surveys continue to provide accurate data on most measures — but only when their samples of telephone numbers include both landline and mobile phones, and only when the completed interviews are weighted to match the demographic composition of the population. That means the weighting procedures that pollsters use are critical to producing accurate results.

The need to weight accurately by race and ancestry is particularly significant when it comes to evaluating the contest between Obama and Romney. As Gallup itself reported in early May, Romney led Obama among non-Hispanic white voters by 54 to 37 percent, while the president had the support of more than three-quarters of non-white registered voters (77 percent). Obama’s support among African Americans on Gallup’s tracking poll stood at 90 percent.

That gap makes the way pollsters account for race hugely important. When pollsters weight their samples to match population demographics, every percentage point increase in black representation translates into a nearly one-point improvement in Obama’s margin against Romney. The difference of just a few percentage points in the non-white composition of a poll can produce a significant skew in its horse race results.

Interestingly, many analysts — Andrew Sullivan, perhaps most notably — are very skeptical of Rasmussen’s polls, which consistently show much better numbers for Romney. Aaron Blake at The Fix has more on the firm’s historical record:

Rasmussen has had both good years and bad years, according to various pollster ratings. While its track record was pretty good in the middle of last decade (2004 and 2006) and average in 2008, after the 2010 election the New York Times’ Nate Silver labeled Rasmussen “biased and inaccurate.” Silver calculated that Rasmussen missed the final margin of the races it polled in the 2010 midterms by an average of 5.8 percentage points.

But Republicans note that Rasmussen did just fine in the last presidential race in 2008. They also note that Gallup, while its top-line number is different from Rasmussen, has shown similar movement in its daily tracking poll in recent days.

“Rasmussen’s track record (’08 and ’10) makes it a very credible polling source in this year’s election,” Romney pollster Neil Newhouse told The Fix in an e-mail.

If there continues to be a disparity between Rasmussen and other polls, expect to hear plenty more about Rasmussen’s numbers — along with the continuing debate about how reliable they are.

Related articles