Two political scientists find that while the 2012 get out the vote efforts boosted turnout, the Obama campaign's effort wasn't better than Romney's. New data gurus are bullish on future future but not on the "death of polling." And the best kind of pie chart is a pizza pie chart. This is HuffPollster for Friday, February 28, 2014.
HOW MUCH DID GET-OUT-THE-VOTE (GOTV) BOOST TURNOUT IN 2012? Quite a bit, argue political scientists Ryan D. Enos and Anthony Fowler : "[W]e compare individuals in the same television media market but different states, allowing us to account for the effects of news coverage and television advertising. We consistently find that individuals living in states that received concentrated GOTV efforts from the campaigns were much more likely to turn out to vote compared to demographically similar individuals in the same media market who lived in a state receiving less GOTV effort."
But was Obama's GOTV better than Romney's? - Enos and Fowler say no: "[D]espite the media accounts of the superiority and sophistication of the Obama campaign, we estimate similar effects for the most Republican and Democratic subsets of individuals, as seen on the left and right sides of the figure, respectively. In other words, both campaigns appear to have been very effective in mobilizing their supporters, and there is no evidence that Obama’s campaign was more effective than Romney’s….When we conduct a more direct analysis of GOTV and turnout, we obtain much larger estimates of campaign effects but no advantage for Obama….Both campaigns deployed significant resources in the traditional forms of GOTV, and both campaigns were extremely effective."
Why did Aaron Strauss reach a different conclusion? - More Enos and Fowler: "[Our results] differ from a recent post by Aaron Strauss who, using similar data and methods, estimates much smaller effects of GOTV and a notable difference between Obama and Romney. What explains these different results? One critical difference is in how the two analyses try to make sure that “all else is equal.” While Strauss’s work uses Catalist’s turnout propensity model to compare individuals across states, our analyses instead employs individual-level demographics to compare individuals in the same media market. As Strauss explains in a follow-up post, analyses that use turnout propensity are likely to be conservative. Our own analyses suggest that Catalist’s turnout propensity scores systematically differ between targeted and non-targeted states, explaining why Strauss’s approach may underestimate the effect of GOTV and overestimate the relative effectiveness of the Obama campaign." [WashPost's Monkey Cage]
DATA IN THE 'NEXT CAMPAIGN' - Politico asked 11 of the "best innovators in politics" to provide quick takes on how technology will change political campaigns. Here are are few data-related excerpts [Politico]:
-Harold Ickes (D), president of data consulting firm Catalist: "Strong data platforms and a wide range of innovative software applications are important in politics, now more than ever. But data and analytics strengthen strategy—they don’t replace it.... The real gains will come from ever richer understandings and deeper relationships across all levels of politics and parts of a campaign."
-Amelia Showalter, director of digital analytics, Obama 2012: "However many whiz-bang innovations and flashy apps emerge in the coming cycles, I think there’s a subtler paradigm shift taking place on political campaigns: Data is coming out of the cave and becoming the new normal. Staffers and volunteers at all levels are learning to use data and to run experiments in their day-to-day campaign efforts, and this may be the biggest game-changer of all...Only a few years ago, it was difficult to get buy-in from the top brass of a campaign for data-driven strategy—even for things that would ultimately save the campaign money. There were too many consultants making too much money being the smartest guy in the room, and few of them wanted to put their decades of expertise (or their percentage of the media budget) up against numbers that might prove them wrong. That’s changing now. And as campaign elites start to champion the use of data in politics, the culture of data and testing will inevitably start to permeate all levels of the org chart."
-Nicco Mele, lecturer, Harvard University’s Kennedy School of Government: "The Death of Polling...Chris Anderson had anticipated the end of sampling when he was editor of Wired magazine in 2008, writing, “Faced with massive data, this approach to science—hypothesize, model, test—is becoming obsolete. … Petabytes allow us to say: ‘Correlation is enough.’ We can stop looking for models. We can analyze the data without hypotheses about what it might show. We can throw the numbers into the biggest computing clusters the world has ever seen and let statistical algorithms find patterns where science cannot.” Polling—a kind of science built on sampling and models—is about to become obsolete."
Mele's comments drew quick rebuke from data scientists and their champions on Twitter:
-Jonathan Robinson (D): "@nicco gets it wrong on the death of polling/sampling, sooooo wrong." [@jon_m_rob]
-Alex Lundry (R): "STOP. Just STOP saying things are dead. Today apparently its polling & TV Ads. Neither of these are going away folks." [@alexlundry]
-Kevin Collins (D): "In fairness, [Mele's] mostly repeating something deeply wrong that Chris Anderson said, but that doesn't make it right...internal and external and construct validity still matter for social science, applied or academic." [@kwcollins here and here]
-Drew Linzer: "'The Death of Polling'? Ha, no. [links to wikipedia article on 'external validity']" [@DrewLinzer, Wikipedia]
-Patrick Ruffini (R) "'Big Data' = larger n=. Not the end of sampling." [@PatrickRuffini]
-Logan Dobson (R): "I like how Polling is Dead because researchers used Facebook to do something polling isn't really meant to do in the first place" [@LoganDobson]
A FCC NEWSROOM STUDY STIRS CONTROVERSY - Byron York sees a government conspiracy to diversify privately-owned media in a 2012 FCC study including a questionnaire sent to newsrooms: "The FCC's action may have, in fact, been...an attempt -- still grossly unconstitutional in its method -- to lay a foundation for a new government push to increase minority ownership of the nation's media outlets….A key advocate of the project to assess whether news organizations are meeting government-defined 'critical information needs' was Mignon Clyburn, an Obama-appointed FCC commissioner and for part of last year the acting chair of the FCC….Part of getting that 'complete picture,' Clyburn argued, was determining what women and minorities most 'need' from media reporting. And if they aren't getting it from the existing media structure -- well, that's why things should change. That's where the CIN study came in….To effect that change, Clyburn started with a method -- sending government contractors into newsrooms to question editors, reporters and other journalists on their decision-making -- that trampled all over First Amendment protections. Now, after the uproar, the FCC has put that study on hold and pledged not to question journalists." [Washington Examiner]
An author of the study explains - Lewis Friedland: "To conservative media from Fox News to Rush Limbaugh, this was an attempt to reintroduce the now-lapsed Fairness Doctrine and for President Obama to take control of America’s newsrooms.….The proposed pilot had three parts. To find out whether community information needs did exist and to what degree, surveys, interviews and focus groups would be carried out, drawn from a broad cross-section of the public. A content analysis of newspapers, broadcast, and Internet outlets would determine whether the information being provided matched people’s expressed needs and how well. Finally, a third component would conduct a “media market census” to “determine whether and how FCC-regulated and related media construct news and public affairs to determine” critical information needs. One aspect of this was a voluntary questionnaire to newsroom decision-makers about their own perceptions of those needs.This last component became the spark that set off the firestorm." [WashPost's Monkey Cage]
HUFFPOLLSTER VIA EMAIL! - You can receive this daily update every weekday via email! Just enter your email address in the box on the upper right corner of this page, and click "sign up." That's all there is to it (and you can unsubscribe anytime).
FRIDAY'S 'OUTLIERS' - Links to the best of news at the intersection of polling, politics and political data:
-66 percent of Americans oppose a law that would allow businesses to refuse service to customers for "religious reasons." [Rasmussen]
-76 percent of Americans oppose Uganda's anti-gay law
[HuffPost]
-A poll of early voters in FL-13 gives Alex Sink a 5-point lead over David Jolly. [St. Pete]
-Geoff Garin (D), Alex Sink's pollster, concedes the Republicans will have a registration advantage of at least 10 points in FL-13. [WaPost's PlumLine]
-Mike Rounds leads his Dem challenger by wide margin in South Dakota's U.S. Senate race [Rasmussen]
-76 percent of Israeli Jews would accept a peace deal [Israeli Peace Initiative]
-Americans see terrorism and Iranian nuclear weapons as the greatest threats to the U.S. [Gallup]
-Kathy Frankovic reviews Hillary Clinton's popularity. [YouGov]
-Steven Shepard and Julie Sobel rank the most most competitive U.S. Senate races; find Republicans poised for major gains. [National Journal]
-Andrew Kohut questions if Democrats are becoming too liberal. [WashPost]
-Anthony Santi (R) ponders a recent drop in the rate of volunteerism. [WPA Research]
-The flu hit New York, California and Nevada especially hard last year. [Gallup]
-46 percent of 12 to 24-year-olds use Snapchat. [Edison Research]
-Planet Money uses data from 3,678 pizza places around the country to show why you should always get the bigger pie. [NPR via Flowing Data]
-Very little pizza is actually eaten for breakfast. [USDA, via @adrienehill]