The increasingly inexact science of polls


Peter Loewen considers the recent failures of political polling.

The problem is not with the first part. Pollsters have developed very clever ways to obtain people’s honest opinions. They can use live people on the phone. They can find respondents over the Internet. They can use “interactive voice recognition,” in which a poll is conducted via a pre-recorded phone message and respondents key in their answers. Data collection is more affordable than ever, and text messaging and smartphone apps are promising even swifter data collection.

The problem is the second part. Pollsters simply do not know enough about who responds to polls via some media, who replies through others, and what kinds of people ignore polling requests entirely. The problem isn’t getting sample, it’s getting good sample. Simply knowing a respondent’s demographic information is not enough to correct for bad sampling. The result is that we cannot extrapolate with sufficient accuracy from our samples to the whole population. We cannot, in other words, know with much confidence the likely outcome of an election before the votes are cast.


The increasingly inexact science of polls

  1. All the more reason to ban polling (other than for internal party use) once the writ is dropped.

    Let people vote on the issues rather than on who the pollsters think is in the lead. Let the reporters report on the issues rather than parroting / pretending to analyze the poll results.

    • What is it with you people and banning things? Because polling is an inexact science, you’d like to ban the supposedly free press from reporting on polls? That’s absurd. How would a reporter “report on the issues” if, for example, they didn’t know that Stephan Dion’s Green Shift was widely reviled by the Canadian public? The public has a right to know what their fellow citizens think of ideas and politicians. In fact, by banning polls after the writ, reporters would have much less information on what issues are important to the voters. I don’t see how that would make for better political coverage.

      That said, anybody who places too much importance on any single poll is a fool. But that’s still no reason to bad reporters from reporting on polls.

      • Rick, if they were polling and then reporting the findings on specific
        issues there might be some value. But they just focus on the race – who
        is in the lead at a given point. Issues are given short shrift; the
        bandwagon is all-important.

        Voting is not supposed to be like
        betting on a horse race, but that’s what it has become for the media and
        far too many voters. It’s time to get back to focusing on the real
        issues. I think a ban on polling – or at least on “horse race” polling –
        will help accomplish this.

        (BTW – which “you people” are you addressing? Supporters of democracy? Of the open and honest discussion of issues?)

Sign in to comment.