No, Political Polling Isn’t Dead

By Nathaniel Scharping | February 2, 2017 1:32 pm

(Credit: jannoon028/Shutterstock)

Political polls may have taken a beating in the last presidential election, but we shouldn’t count them out quite yet.

After President Donald Trump, who was predicted to lose the election by a wide margin, emerged victorious from the 2016 presidential race, stories about polls were thrown into the “fake news” shredder. Although the fault may have lain with how we interpret them, polls lost a significant amount of hard-earned trust in the eyes of the public.

Polls Down, But Not Out

If we drill down to the data, polls remain a potent, though not infallible, tool for determining how the democratic process might play out. In a paper published Thursday in Science, researchers examined more than 600 international elections across seven decades and found that polls were reliable predictors of election outcomes—90 percent of the time. They then built a model based on polling data and backed up their tough talk with several real-world tests, finding that they were able to successfully predict more than 80 percent of 36 ongoing elections.

Their model relied on other factors besides polling, of course, such as the level of democracy, whether or not an incumbent ran (incumbents have a slight edge) and foreign relations. When they took polling data out of the model, however, they saw a substantial drop in predictive accuracy. Even in places where polling data was poor, they say that it still affected the reliability of their model, indicating that polls generally picked the right candidate.

Improve, Don’t Abandon

Though polls may be important, some refinements seem to be in order. The researchers found that they could improve their predictions by accounting for biases in the polls—a tendency to pick one candidate over the other based on differences in the type of populations sampled, among other things. They also created an updated model by “smoothing out” weaknesses in polling data by accounting for regional variations, whether the incumbent candidate is running and economic factors.

This paper is part of a special section in Science looking at the power of prediction. Other essays cover the accuracy of predictions of violence and scientific breakthroughs, the role of artificial intelligence in predicting the best policies and ways to make predictive science better.

Pollsters, and the statistical machinations that underlie their predictions, may have been mildly embarrassed in November, but the presence of polls, and predictive science in general, isn’t going anywhere—we predict. The authors point out that statistical models never claim the ability to peer into the future, they only rank various outcomes as more or less probable. Even someone with a 16 percent chance of victory, as Trump had in the researchers’ model, will win sometimes. Add to that the fact that most polls tracked the outcome of the general election fairly well, and it’s safe to say that polls will remain a important tool for political scientists.

The authors sum it up best themselves in the last line of their paper:

“We predict that reports of the death of quantitative electoral forecasts are greatly exaggerated.”

CATEGORIZED UNDER: Space & Physics, top posts
MORE ABOUT: mathematics
  • John C

    The polls showed an overwhelming loss for Trump, and absolutely no path to 270 electoral college votes.

    However, everywhere I drove outside cities and college towns I saw Trump lawn signs, many hand made. Bumper stickers, etc. Here in N.J., a blue state, but also when we took a vacation through New England in October – Mass., Vermont, N.H. Literally 10 to 1 over Hillary signs.

    I said to my wife, there’s something going on under the surface in this country that the polls just aren’t picking up. And certainly not the media.

    The polls missed an enormous phenomenon that even I could see clear evidence of.

  • Uncle Al

    we shouldn’t count them out quite yet” Political polling is less than meaningless – it is corrupt, for sale to the highest bidder.

    Youtube v=zT0Rjc6jKCg “I thought he was running as a joke.”
    Youtube v=O7Bkh9Wo2vE HER chance was “above 99%”

    Trump spent $600 million less on his campaign than HER. HER could not fill large rooms while Trump overflowed stadiums. HER got trumpled in the Electoral College, then trumpled again on the recount.

    polls will remain a important tool for political scientists” Stalin, Mao, Castro, Pol Pot, Salvador Allende, the Kim Jungs, Hillary Clinton…didn’t they each and all poll 100%?

  • OWilson

    Polls, like just about all other aspects of public life have become politicized. It’s a fact!

    Who could take seriously a CNN poll involving Trump given the level of their absolute revulsion towards him?

    In two recent elections they shamelessly joined the battle for the candidate on the left, (Candy Crowley against Romney, and feeding debate questions in advance to Hillary)

    The other alphabet networks are no better, and the major newspapers are already heavily invested in their candidate, by their official endorsement.

    They need to show their candidate as the inevitable winner, it helps the money raising effort, which is what campaigns are all about.

    The left lobby are less concerned that Hillary went down to defeat, than they are about the $2,000,000,000.00 or so of good left wing money that went down the drain!

  • Cliff Clavin

    Every time I get called for a pole I lied. For some reason I seem to get called a fair amount. Maybe it’s because I am not part of any political party.

    • OWilson

      It is mostly Democratic voters that don’t appreciate the privilege of the “secret ballot” and are happy to tell a stranger on the telephone, who they are going to vote for! :)

      I just ask them who THEY are going to vote for and they hang up in a hurry!

      Like when the pretty young thing behind the counter at Radio Shack asks me my phone number, I ask, “What’s yours?”

      Most of the younger ones don’t get the joke!

      • Cliff Clavin

        I like to do as much as I can to distort the results of the survey/poll.

  • Ken_g6

    Five Thirty Eight did bias accounting. They were the most accurate of the polling aggregators I saw, giving trump almost a 1 in 3 chance of winning.

    And national polling was very accurate. Hillary did win the popular vote. I think some of the problem was pollsters simply didn’t poll much in Great Lakes states where nobody thought Trump would win.

    • OWilson

      Hindsight is 20/20.

      The goal was to win 270 Electoral College votes That’s what makes you President.

      A wise Trump spent hardly any time/money in the populous States, of New York and California.

      He knew exactly what he needed to do to win, and did exactly that! :)

  • Cliff Clavin

    One would think that the left would want the polls to be very accurate. If they had been accurate in this election they would have seen Trump as the presumptive winner and might have worked harder to change the outcome. Personally I think it’s pretty cool that they like to delude themselves with inaccurate polls.


Discover's Newsletter

Sign up to get the latest science news delivered weekly right to your inbox!


Briefing you on the must-know news and trending topics in science and technology today.

See More

Collapse bottom bar