James D. Morgan/Getty Images(WASHINGTON) — A task force of research experts said there’s “little backing” in 2016 election polling data for the “shy Trump” hypothesis, which is the theory that Donald Trump supporters were unwilling to tell pollsters they favored him because they thought it was socially unacceptable to do so.
The special American Association for Public Opinion Research (AAPOR) panel found that national polls were “generally correct,” but state-level polling across Rust Belt states that were crucial to the president’s victory showed some “large, problematic errors” and “failed to adequately measure support for Trump.”
“The day after the election, there was a palpable mix of surprise and outrage directed towards the polling community, as many felt that the industry had seriously misled the country about who would win,” the panel’s 104-page report said, before diving into a detailed analysis of polling in the lead-up to the election.
The Trump campaign urged his supporters not to believe poll results before the election, which, at the time, showed Democratic nominee Hillary Clinton was likely to win.
To explain why some state polling did not align with the election’s outcome in several key states, the panel of public opinion and survey research experts pointed to a “real change in vote preference during the final week or so of the campaign” and the failure of many state polls to include the correct proportion of non-college graduates — a core Trump constituency.
The data showed that the Trump-Clinton margin in national polls was off by an average of 2.2 percentage points, among the most accurate in U.S. polling back to 1936. But state-level polls were off by an average of 5.1 percentage points, according to the report.
The panel found little evidence for one major theory in the wake of the election: that Trump voters did not demonstrate their support for Trump in polling because they did not believe it was socially acceptable.
If the “shy Trump” theory were accurate, experts said, they would expect Trump’s support to be lower in live-interviewer polls than robo-dial polls, because people would be more hesitant to tell an actual human being they supported Trump. But the study’s results were “inconsistent” with expectations of that theory.
No ‘evidence of bias’
The data also “does not show evidence of bias” when it comes to the idea of differential non-response, a theory that Trump voters were less likely to participate in a poll than people who supported other candidates. But it does say the findings “do not rule out the possibility.”
The report also says there is evidence, particularly in the upper Midwest, that voters who told pollsters they were undecided or voting third party ultimately ended up casting their ballots for Trump.
But the committee doesn’t point to FBI Director Jim Comey’s decision to reveal new emails in the Clinton email scandal as the main reason for Clinton’s late skid.
“We would conclude there is, at best, mixed evidence to suggest that the FBI announcement tipped the scales of the race,” the report said, adding that it is “reasonable” to speculate that Clinton’s slide began as early as Oct. 22 or 23.
The report says state-level polling may have gotten by without weighing its results based on education level in 2012 because the split between college graduates and Americans without a college degree was not as drastic. But in the 2016 election, where education was such an influential variable, that method “completely fell apart.”
“Adjusting for over-representation of college graduates was critical, but many polls did not do it,” according to the report. It adds that voters with higher education levels are more likely to participate in a poll than voters without a degree. “Many polls, especially at the state level, did not adjust their weights to correct for the over-representation of college graduates in their surveys, and the result was over-estimation of support for Clinton.”
Swing-state polls missed education
The study showed that the majority of national polls adjusted their results for education, but only one in three — or even fewer — swing-state polls where Trump won weighted their results to education, including just 18 percent of Michigan polls and 27 percent of Wisconsin polls.
Other factors, like the order of names on the ballot and the possibility that changes in turnout from 2012 to 2016 resulted in inaccurate “likely voter” models, may have contributed to the problem. But the report added that there is less compelling evidence for such reasons and they did not alone account for the error in state polling.
Based on data from the Pew Research Center callback survey — which calls the same people before and after the election to see whether their actual vote was consistent with their answer to the pre-election poll — 11 percent of people told pollsters one thing before the election but cast their ballots differently. The committee called those numbers “quite typical.”
But in 2016, inconsistent respondents voted for Trump by a 16 percentage point margin, the largest since Pew began the callback survey in 2000.
Copyright © 2017, ABC Radio. All rights reserved.