Victory Lab

Why Obama Is Better at Getting Out the Vote

Lots of door-knocking—and years of statistical analysis.

Democratic volunteers Chris Lettero and Matt Lattanzi knock on apartment doors while canvasing for votes in Youngstown, Ohio

Photo by John Moore/Getty Images.

CINCINNATI—By the time Mika Darley-Emerson stepped out of the light drizzle and into a doorway’s modest refuge, she’d already forgotten about the instructions she had been given about how to talk to a prospective voter.

Four years ago, as she was beginning her first year as a graduate student at the University of Cincinnati, Darley-Emerson had coordinated a system of early-vote shuttles for the Obama campaign. This past Saturday, she returned to the city from the suburbs, where she now has a baby and a partially completed dissertation, to help get out the vote for the president’s re-election. “We go where the volunteers are needed,” the winsome 34-year-old said. Darley-Emerson had a script that was supposed to direct her interactions with voters, but it was buried under the list of names and maps of the middle-class Westwood neighborhood she had been assigned. She’d also received training that morning emphasizing that at the start, volunteers were to find out which candidate the voter supported before moving ahead to other questions. The purpose of a GOTV canvass is to mobilize only those known or highly likely to be supporters.

The fourth house Darley-Emerson visited was home to an African-American man in his 30s who came to the door in a sweatshirt emblazoned with the word ETHIOPIA. Darley-Emerson introduced herself, and immediately asked him if he had taken advantage of Ohio’s early-voting window. He explained that he was a nursing student and that a trip to the downtown board of elections wasn’t easy to schedule. Soon Darley-Emerson was talking him through the various transportation possibilities, and the relative merits of garage and street parking. Together they made a plan—he would drive downtown to vote mid-afternoon Sunday—and Darley-Emerson moved to the next item on her mental checklist: pushing this likely voter to move down his ballot to support Ohio’s Democratic senator, Sherrod Brown.

In so doing, Darley-Emerson had the type of psychologically meaningful interaction that years of randomized-control trials had shown would increase a citizen’s likelihood of casting a ballot. But she had overlooked the opening, threshold question on her script, the one she’d been trained to start with: Who do you support for president? “I forgot to ask that first,” Darley-Emerson acknowledged after retreating to the sidewalk, and then joked that she was as “an absent-minded teacher” getting an early start on her career. “Part of why I felt a little more comfortable making that mistake,” she reflected, “is most of the people on our list at this point are supporters.”

Darley-Emerson’s rounds—and those of hundreds of thousands of other canvassers and callers in the closing hours of the election—may look like the basic work of campaigns, the slog of door knocks and repetitive phone calls. But as is the case with much of Obama’s campaign, the dutiful fieldwork is undergirded by sophisticated analytics unmatched by his Republican opponents. The houses on Darley-Emerson’s list were not only likely to contain supporters, but supporters for whom a visit from a canvasser could make all the difference.


Matt Reese, a legendary Democratic consultant who played a crucial role in organizing West Virginia for John F. Kennedy’s presidential primary campaign, had a simple explanation when asked what field operatives do. “I wish God gave green noses to undecided voters, because between now and election eve, I’d work only the green noses. I wish God gave purple ears to nonvoters for my candidate on election eve, because on election day I’d work only the purple voters,” Reese would say when asked about his methodology. “The ones we go after are nonvoters who are for us and the undecided voters.”

The challenge for a campaign, of course, is to sort voters into those two categories without the benefit of such visible markers. In an ideal world, a campaign would interview every voter to discern his or her likelihood of casting a ballot and the candidate he or she supports. But no campaign has the money or manpower to track down and survey even a sizeable fraction of the voting public, either through volunteers or paid operations. So campaigns use data about the electorate to increase the quality of their guesses about which voters are likely to have green noses and which ones purple ears. For decades, political targeters had to use geographic or demographic heuristics (classifying precincts based their past vote performance or Census tracts based on their complexion) to sort voters into those categories en masse. With the individual-level voter data and statistical analysis available to today’s campaigns, they can now sort voters one by one.

Over a two-week stretch starting at the end of July, the Obama campaign’s analytics department contacted 54,739 voters from paid call centers and asked them how they planned to vote. Obama’s databases already knew a lot about the approximately 180 million registered voters in the United States (and even a bit about those who weren’t registered, in a way that could help guide the campaign’s efforts to enroll them). The goal was to collect intelligence about potential voters’ 2012 intentions and distill that down to a series of individual-level predictions. The most important of these scores, on a range from 0 to 100, assessed an individual’s likelihood of supporting Barack Obama and of casting a ballot altogether.

Modeling turnout was thought to be easier than modeling support, since how citizens vote is a private concern but whether or not they do is a matter of public records. In reviewing the attributes of 2008 voters, Obama’s analysts confirmed that the most useful predictor of turnout was past vote history. For years, campaigns would sort voters by these criteria—assuming that someone who had participated in two of the past four elections was more likely to turn out than someone who had turned out for only one—and the Obama campaign used this as the basis for a basic typology. Those who had voted in the 2010 elections were classified as “midterm voters”; those who had voted in 2008 but not in 2010 were called “sporadic voters.”

But splitting the electorate into only three or four categories didn’t leave much opportunity to assign priority to individual voters, or room to draw granular distinctions among them. More perilously for Obama, a pure reliance on vote history didn’t help to predict the behavior of young voters, because the campaign simply did not have enough of a track record to assess. The president will rely for his re-election on young people, who overwhelmingly supported him in 2008 but tend to be fickle voters. Which kids had a thin voting history because they only recently became eligible to cast a ballot and which ones because they weren’t the type of people who could be counted on to vote?

Obama’s analysts built statistical models to pull out other factors that distinguished voters from nonvoters. Socioeconomic factors like income and housing type played a role; those who lived in multi-tenant dwellings, for instance, were less likely to vote. But within those households Obama’s analysts found a twist. A voter living with other people who had a demonstrated history of voting was predicted as more likely to turn out herself.

The Obama campaign’s algorithms ran the numbers and predicted the likelihood that every voter in the country would cast a ballot, assigning each a turnout score. Obama’s analysts knew how good their support score was because they polled a new group of voters to validate it: 87 percent of the time it would accurately predict an individual’s preference. But it would be impossible to confirm their algorithm’s turnout predictions until after the election. But they did their best to assess its accuracy, by calling voters and asking them how likely they are to vote. Analysts know that people are poor predictors of their future behavior, but they got answers that confirmed that their rankings were at least sensible. Among the 10 percent of voters seen as most likely to vote, 95 percent said when contacted that they definitely would. Based on 2008 figures, Obama’s analysts assumed that 40 percent of those who told callers that they would “definitely not” vote ultimately would. “Possibly,” the analytics department advised in a September memo, this was “due in part to our GOTV efforts among these voters.”


In late October, or as early as September in early voting states like Ohio, campaigns shift from registering new voters and persuading wavering ones to harvesting votes from people they already count as on their side. Such get-out-the-vote operations include pre-election reminders, providing information on polling-place locations and absentee-ballot protocols, and, increasingly, psychological nudges informed by the behavioral sciences—all delivered over personalized channels like mail, phones, or in-person visits. Indiscriminately subjecting voters who might support your opponent to such motivators is considered an unsustainable risk. As a result, field organizers typically move a voter into a so-called GOTV universe only if he or she has told a caller or canvasser that they are a supporter, or statistical models predict they are likely to go your way.

Campaigns tend to focus their mobilization efforts on voters who have been assigned high support and mid-range turnout scores. Those with turnout scores outside a span of, say, 30 to 80 are not worth the effort: Those above it are self-motivated enough to vote already, and those beneath it unlikely to do so under any circumstances. Democrats approach the question of prioritizing voters for turnout in much the same way as Republicans. Obama, however, goes a step farther.

Since 2008, Democrats have administered randomized-control experiments to test the impact of GOTV contact on voters with different score combinations, with the goal of quantifying where those contacts are most likely to produce a net vote. The most fruitful terrain turned out to surround voters with turnout scores centered around 45. Delivering a GOTV contact to a voter with a 100 support score and a 45 turnout score increased the likelihood of netting a Democratic vote by 4.5 percent; delivering a GOTV contact to a voter with a 75 support score and a 45 turnout score increased the likelihood of netting a vote by 2.7 percent.

Obama’s analytics department synthesized all of this research into a new GOTV score that combines predictions about one’s likelihood of voting and supporting Obama. It, too, ranks voters from zero to 100, but this one doesn’t assess voters’ characteristics so much as prioritize them based on their susceptibility to the campaign’s efforts to modify their behavior. When canvassers like Darley-Emerson get a list of names, it has been edited according to the one criterion that matters: how likely her visit is to generate a new vote towards the president’s re-election—whether the canvasser remembers to ask who the voter is supporting or not.