A wisp of sunlight on the horizon, standing on a long line waiting for my polling place to open chatting with two young women, first time voters, proud to be electing the first female president. November 8th, 2016.
Nate Silver (fivethirtyeight blog) assuring us for weeks than Hillary was far ahead in the polls. We forgot the mantra of pollsters: never having to say we’re certain.
What went wrong?
We’re two weeks from Election Day in an election that will determine the fate of our nation, the future of democracy.
I looked back at a blog I posted on October 20, 2016, “Can the polls be wrong: Hillary is up 8 points, no, Trump is up by 1 point, What’s going on? Why are the polls varying so much?” I took a deep dive into the polling process, a deeply flawed process that is meant to grab headlines, glue eyes to the screen. If a poll “predicts” a winner the pollsters can pat themselves on the back, if they’re wrong it’s the fault of the public, the “sample” wasn’t being honest.
2016 wasn’t a good year for pollsters; they were wrong predicting the Brevet vote in the United Kingdom and wrong in the presidential.
Remember: a poll is a photograph in time of a sampling of likely voters. The sampling should 1) be restricted to prime voters, persons who voted in four of the last five elections, 2) reflect the likely voters by gender, race, party affiliation, income and education, the more areas the more accurate the poll, 3) and large enough to reduce the margin of error. (See my blog “Should you trust the polls?” from a few weeks ago – I discuss the polling process in detail).
In 2016 the FBI head James Comey’s announcement that he was re-opening the Hillary e-mail investigation couldn’t be predicted, also, Bernie voters who stayed home or voted for third party candidate Jill Stein, and the Trump voters who were ”hiding in the weeds,” in other words, polling, although it uses dense mathematical models, is imperfect.
Nate Silver, tries to reassure voters, in his latest, “8 tips to stay sane in the final 15 days of the campaign,” I think he creates more anxiety and tries to insulate himself from another polling catastrophe.
Pew Research does a superb job in parsing the world of polling (Read here),
The barriers to entry in the polling field have disappeared. Technology has disrupted polling in ways similar to its impact on journalism: by making it possible for anyone with a few thousand dollars to enter the field and conduct a national poll. As with journalism, there are pluses and minuses to this democratization. There has been a wave of experimentation with new approaches, but there has also been a proliferation of polls from firms with little to no survey credentials or track record. In 2016, this contributed to a state polling landscape overrun with fast and cheap polls, most of which made a preventable mistake: failing to correct for an overrepresentation of college-educated voters, who leaned heavily toward Hillary Clinton. Some newcomer polls might provide good data, but poll watchers should not take that on faith.
Polls are widely viewed and widely distributed leading to shoddy polling, weather reports tend to excessive predictions of adverse weather: eyes on the screen and computer “clicks” drives advertising revenue; “if it bleeds it leads.”
Polls rarely mention “margin of error,” and never mention what it means. If a margin of error is “plus or minus 3%” and the poll predicts a 52-48 lead the outcome is within the margin of error: a “statistical tie.”
The real margin of error is often about double the one reported. The notion that a typical margin of error is plus or minus 3 percentage points leads people to think that polls are more precise than they really are. Why is that? For starters, the margin of error addresses only one source of potential error: the fact that random samples are likely to differ a little from the population just by chance. But there are three other, equally important sources of error in polling: nonresponse, coverage error (where not all the target population has a chance of being sampled) and mismeasurement. Not only does the margin of error fail to account for those other sources of potential error, it implies to the public that they do not exist, which is not true.
They haven’t stapled the chip into earlobes yet, (I think!); the best counter to polling is advocating for your candidate: donations to campaigns, joining a campaign, manning phone banks, calling friends and neighbors; BTW, simply posting on Facebook is not participating in a campaign, it is altogether likely your Facebook friends agree with you.
In a normal election year (whatever that means) polls close and a few hours later we know the results. This year we may have a long wait, hours, days or weeks, or maybe, longer. Thirty million mail-in and early voting ballots have already been cast; in some states the counting of mail ballots will extend for days. Candidates may challenge various aspects of the counting of mail-in and early-voting ballots.
Who decides disputed slates of electors? Ever hear of the Electoral Count Act of 1887? (Read here).
A great year for Civics education.