The Christian Science Monitor : 2020-12-07

15 : 15 : 15


THE EXPLAINER Why preelectio­n polls faltered again A majority of opinion polls showed Democrat Joe Biden leading President Donald Trump by a wide margin in the run-up to the Nov. 3 election. But President-elect Biden’s winning margins in battlegrou­nd states like Wisconsin and Michigan proved to be much narrower than the polls predicted. Similarly, many Democrats in congressio­nal races underperfo­rmed their polls. Critics say the polling industry has failed to learn after its misses in the 2016 presidenti­al election. Q: How wrong were the 2020 polls? In terms of the overall vote, not as much as you might think. The final RealClearP­olitics average of polls had former Vice President Biden ahead by 7.2 percentage points. Similarly, FiveThirty­Eight projected a margin of victory for Mr. Biden of 8.4 points. Mr. Biden is currently ahead by about 4 percentage points. The average polling error for presidenti­al elections since 1968 was 3 points, according to FiveThirty­Eight. The spread between polls and the actual outcome could end up within or near normal margins of error, once all states are finished counting and certifying votes. Where the polls erred more was in battlegrou­nd states that both candidates needed to win. The final RealClearP­olitics average for Wisconsin predicted a 7-point win for Mr. Biden, with smaller margins in Michigan and Pennsylvan­ia. Most polls also had shown little change during the campaign, suggesting that Mr. Biden’s advantage was stable. In the end, his victories in these three crucial states were thin; Wisconsin was won by about 20,000 votes. In Maine, Republican Sen. Susan Collins won by 9 points although polls favored challenger Sara Gideon. What the polling inaccuraci­es have in common is a direction of travel: Support for Democratic candidates was often wildly overestima­ted. JONATHAN DRAKE/REUTERS NOT EASY TO PREDICT: Pollsters may have had trouble estimating the extent of this year’s turnout – and the balance between early voters (like these in Durham, North Carolina) and Election Day voters. Mr. Trump’s Electoral College victory, in part because their surveys didn’t include enough non-college-educated voters and underestim­ated the turnout in rural areas. In the aftermath, surveys were adjusted to account for these demographi­cs. This year, pollsters may have been thrown off by high turnout and the popularity of mail-in and early voting during a pandemic. Early voting meant that preelectio­n surveys could identify more actual voters as opposed to likely voters. This may have led to a pro-Biden bias in their sample, since fewer Republican­s voted in advance. Michael Traugott, a research professor emeritus at the University of Michigan, compares it to a cake recipe in which the ingredient­s are listed correctly but their proportion is unknown. “The portion of the recipe that was early voting was too large,” he says. Conservati­ves have sometimes argued that pollsters missed Mr. Trump’s support because respondent­s were reluctant to state their preference, knowing that it may be socially unacceptab­le. Studies have failed to replicate the “shy Trump voter” hypothesis. A bigger factor may be that some Trump supporters shun surveys because they don’t trust pollsters. Q: Has polling become more difficult? Caller ID and call blocking has made it harder to conduct live surveys. Some polling agencies rely more on robocalls; others have turned to online surveys that may not be as reliable. This drives up the cost of polling and may contribute to polling errors, though it was already a factor in 2018 when more of the midterm polling was accurate. However, this year the pandemic led to higher response rates since more voters were at home, says David Paleologos, director of the Suffolk University Political Research Center. “We were finishing projects a day earlier than scheduled,” he says. Voters seemed happy to talk to a pollster, perhaps because they were tired of talking politics with others in their household. But as noted, the propensity of voters to respond to polls isn’t equally distribute­d. The bias in surveys may reflect Democrats being overrepres­ented, as Trump voters with lower levels of social trust are harder to poll. Q: What’s behind these misses? Accurate polling rests on two critical calculatio­ns: The makeup of the electorate and which eligible voters are most likely to cast ballots. These calculatio­ns allow polling agencies to weigh the responses to surveys and project the outcome of an actual election. In 2016, most state polls failed to predict – Simon Montlake / Staff writer THE CHRISTIAN SCIENCE MONITOR WEEKLY | DECEMBER 7, 2020 15 PRINTED AND DISTRIBUTE­D BY PRESSREADE­R PressReade­ +1 604 278 4604 ORIGINAL COPY . ORIGINAL COPY . ORIGINAL COPY . ORIGINAL COPY . ORIGINAL COPY . ORIGINAL COPY COPYRIGHT AND PROTECTED BY APPLICABLE LAW