There's been a mild freakout over this:
A new online study finds that Republicans and independents are twice as likely as Democrats to say they would not give their true opinion in a telephone poll question about their preference for president in the 2020 election. That raises the possibility that polls understate support for President Donald Trump.
Some 11.7% of Republicans and 10.5% independents said they would not give their true opinion, vs. 5.4% of Democrats, according to the study by CloudResearch LLC....
CloudResearch conducted the survey online but inquired about surveys that are conducted by phone. It first asked participants for their political preference, then asked how they felt about divulging their preference for president in a phone poll. Later, it asked whom they actually did support for president.
So some people are reluctant to tell pollsters that they support their candidate, and we know that more Trump voters than Biden voters feel this way because they were asked by a pollster and they said they ... supported Trump? How do we know the respondents were telling the truth in this survey? Maybe a percentage of the people who said they supported Biden were the real Trump voters.
The argument is that Trump voters will be honest in an online survey but not in a phone survey, because they're "shy" about acknowledging support for their candidate when talking to a human being, or for some other reason. Here are some responses CloudResearch got after asking reluctant Trump supporters to explain their reticence:
I don’t believe the information would be confidential and I think it’s dangerous to express an opinion outside of the current liberal viewpoint.”
“Well I probably wouldn’t give my opinion period, but if pushed, I would not give my real opinion for fear of reprisal if someone found out.” ...
“My answers could be recorded so I don’t really trust such phone conversations.”
“I do not discuss politics — let alone with a total stranger on the telephone.”
“I don’t always trust phone call surveys. I wouldn’t want to be bombarded with phone calls and political mail.”
“I don’t want my opinion associated with my phone number.”
What's bizarre about this is that none of these people seem to realize that activity on computers is also tracked -- if anything, more efficiently than what's said to a pollster -- and they're probably less safe from follow-up activity answering an online survey. Maybe the sector of the population that doesn't grasp that point, which should be obvious to all of us, skews Trump. It's possible.
But as CNN's poll analyst, Harry Enten, noted earlier this month, there's not much evidence of a discrepancy right now between phone polls and online polls, and Biden is leading comfortably in both:
Biden's national lead is still 8 points in polls that don't use live interviews at this point. That is a little lower than in polls that do use live interviewers and call cell phones, though that gap has only recently appeared and may just be a statistical artifact.
In July, when The New York Times and Siena College released a poll (conducted by telephone) that showed Biden with a significant lead over Trump, Nate Cohn of the Times reported that more Republicans than Democrats completed the Times/Siena survey:
Over all, telephone calls to registered Republicans or those who participated in a recent Republican primary were about 12 percent likelier to yield a completed interview than calls to Democrats were. This seemingly noteworthy difference can be explained by well-known demographic biases in polling: Older, rural and white voters are likelier than young, urban and nonwhite voters to respond to surveys. After these factors were controlled for, Republicans were no likelier than Democrats to respond to the survey.
But what about 2016? On a national level, the polls were pretty good -- the final Real Clear Politics average showed Hillary Clinton leading by 3.2; she won the popular vote by 2.1. Charlie Cook of the Cook Political Report says that problems with state polls were about demographics, not failure to account for shy voters.
And where were the polls off in 2016? In those very states of Michigan, Pennsylvania, and Wisconsin. Postelection studies revealed that, nationally, there was a slight over-sampling of whites with college degrees and a slight under-sampling of whites with less than four-year degrees. Since then, most pollsters have begun to correct for that, weighting white voters by level of educational attainment.
Shortly after the 2016 election, when he was still at FiveThirtyEight, Harry Enten concluded that the "shy Trump voter" factor was, oddly, most prominent in Trump states.
... if the ["shy voter"] theory is right, we would have expected to see Trump outperform his polls the most in places where he is least popular — and where the stigma against admitting support for Trump would presumably be greatest.... But actual election results indicate that the opposite happened: Trump outperformed his polls by the greatest margin in red states, where he was quite popular. The two states that had the largest polling error for Trump were Tennessee and South Dakota, where Trump won more than 60 percent of the vote. Meanwhile, Trump underperformed his polls in states where the stigma against him would seem to be strongest: deep-blue states like California, Hawaii, Massachusetts, New York and Washington.
There might be a "shy Trump" phenomenon. But the data nerds are watching for it and conducting and analyzing polls in ways that attempt to identify it and compensate for it.
Besides, these folks don't seem particularly shy.
Posted with permission from No More Mr. Nice Blog