It's Another 'Disaster for the Polling Industry'

Pundits point to social desirability bias
By Arden Dier,  Newser Staff
Posted Nov 4, 2020 2:09 PM CST
Why the Polls May Have Got It Wrong
A Japanese and a US flag are seen in front of a TV monitor showing a news program live broadcasting on the US presidential election at a foreign exchange dealing company in Tokyo on Wednesday.   (AP Photo/Eugene Hoshiko)

With six states still to be called, much about the 2020 election is up in the air. What is clear is that President Trump did far better than most polls suggested he would, as also was the case in 2016. Surveys gave the impression of "an easy win for former Vice President Joe Biden, a Democratic pick-up in the Senate, and gains for the party in the House," as David A. Graham writes at the Atlantic. "Instead, the presidential election is still too close to call, Republicans seem poised to hold the Senate, and the Democratic edge in the House is likely to shrink." So what happened? Click through for some theories.

  • Dishonesty: At the Hill, columnist Keith Naughton notes pollsters may not be getting honest answers from respondents on certain issues. On the coronavirus pandemic, for example, "it may be that voters feel that expressing greater concern over their economic circumstances as opposed to public health is too embarrassing and not appropriate," he writes. "Yet, when they have to actually vote, economic concerns drive decision-making."
  • Social desirability bias: Poll response rates are rumored to be around 3%, "a very thin foundation on which to predict a presidential election," Salvatore Babones writes at the Sydney Morning Herald. But he also points to social desirability bias, the idea that respondents give answers they think will be viewed favorably by pollsters. He notes Rasmussen, which uses a pre-recorded voice in its telephone surveys, had decent predictions in Florida and also "came closest to predicting the outcome of the 2016 election."
  • Forget polls altogether: Polls are usually imprecise, which is why it's best to look at averages. But "the final 538 average had Joe Biden winning Florida by 2.5 points" when Trump won the state by that same margin, John Podhoretz writes at the New York Post. He therefore suggests we abandon political polling "before our last brain cells are destroyed." It's "a fraud," he writes. "It claims to measure something that, it is now unmistakably clear, cannot be accurately measured."
  • "Worthless as a milk bucket": Former Arkansas Gov. Mike Huckabee would agree with Podhoretz. "I think polling is as obsolete as an 8-track tape and is worthless as a milk bucket under a bowl," he told Fox News on Wednesday. "Let's never hear about polling anymore."
  • Who are we?: At the Atlantic, Graham notes the election was clearly "a disaster for the polling industry." But "the greatest problem posed by the polling crisis is not in the presidential election," he writes. Rather "the failure of the polls leaves Americans with no reliable way to understand what we as a people think outside of elections—which in turn threatens our ability to make choices, or to cohere as a nation."
(More Election 2020 stories.)

Get the news faster.
Tap to install our app.
Install the Newser News app
in two easy steps:
1. Tap in your navigation bar.
2. Tap to Add to Home Screen.