With polls coming out nearly every day on nearly every topic, it is time to revisit the topic of national polling. The first issue is statistical accuracy. A typical three-day poll of 1000 people, if proportioned among the 3000 counties, can accurately represent American adults 19 out of 20 times within three percentage points.
The real question about the polls isn’t whether they are statistically accurate but whether they are polling the right people and whether the people being polled are giving honest answers. We should assume that reputable polling firms do conduct polls that accurately mirror race, sex, age, geography, and educational makeup.
This presents a problem in trying to determine if the right people in the right percentages have been polled. Too often, one party or group ends up being over sampled. And if the poll is about likely voters, there is the problem of accurately determining if someone being polled will actually be voting in the election.
But the biggest problem is that people being polled don’t always give honest answers. Two researchers at the University of Arkansas found that people with unpopular opinions feel “the need to conceal their true voting intentions.”
In the past, this was called the “Bradley effect.” Los Angeles Mayor Tom Bradley was an African-American who lost in 1982 despite being ahead in the polls. Some voters told pollsters they were undecided or going to vote for Bradley because they didn’t want to say they weren’t voting for the black candidate.
But this has become an even bigger problem when you are polling people about Donald Trump. They have seen videos of what happens to people wearing a MAGA hat. They have heard about people being fired, abused, and doxed if they say they voted for or will vote for Trump.