What do pollsters want?

Glen Newey

YouGov's latest poll projection has the country heading for a hung parliament. This is certainly the most eye-catching forecast in the election so far, aimed to fuel lumpen-commentariat reaction about the closing gap between the Tories and Labour.

After the 2015 general election, the polling biz ended up with egg – in fact, a full-size battery farm – on its face, and it didn’t do much better with last year’s US presidentials or the EU referendum. Part of the problem lies in guesstimating outcomes from poll numbers, given the idiosyncrasies of the electoral system. YouGov says it has about 75 respondents per UK parliamentary constituency – far too few for robust predictions at that level. But that’s not the whole story in the UK, where polls haven’t been much good even at estimating the popular vote in the country as a whole.

Like credit rating agencies, pollsters such as YouGov are private businesses, with an interest in talking up their own performance. When the information they dispense proves inaccurate, business demands inaccuracy about that, too. YouGov’s CEO Stephan Shakespeare boasts that YouGov’s new MRP model (‘multiple regression and post-stratification’; it’s explained here by ‘YouGov’s chief scientist’ Doug Rivers) for predicting the election outcome ‘is something we publicly tested during last year’s EU campaign and it always had “Leave” ahead’. Not quite. In a tweet on the eve of the referendum, YouGov’s freelance wonk Benjamin Lauderdale said that the result would be within the 48-52 per cent range – but didn’t say who’d win. 'Estimates are now within 0.1% of 50-50’. A pseudo-exit poll YouGov did after voting ceased at 10 p.m. on 23 June 2016 reported leave at 48 and remain at 52 per cent – though, in fairness, that didn’t use MRP (re-analysis of the data using MRP had the result as a dead heat).

Modelling is the point where voodoo enters the system. Raw data consists of raw responses to pollsters’ questionnaires, which somehow have to be parlayed into a prediction. The main gaps concern demographics, and the relation between expressed intention and action. Explaining MRP, Rivers tells us that ‘YouGov has estimated the number of each type of voter in each constituency,’ which prompts the question what types there are. What type are you? Maybe the type that doesn’t vote, or gives flippant answers to pollsters. No doubt there are numbers to scale that, too.

Pollsters have an interest in being seen as generally accurate. But they are also, even willy-nilly, intervening in as well as observing the electoral process. Shakespeare stood as the Conservative candidate for Colchester in 1997 and was formerly a member of the Socialist Workers’ Party; he founded YouGov in 2000 with Nadhim Zahawi, the Tory MP for Stratford-on-Avon before the dissolution. Perhaps they see their role in present circumstances as that of warning against complacency. People who think the election is a done deal tend to vote with their arse. More significantly, pollsters have an interest in making elections seem tighter than they are. So do the print and e-media, as do the political parties. All have more attention paid them if ‘the race is too close to call.’ Newspaper coverage of poll 'findings' is a free advertising platform for YouGov and its ilk. Its latest poll, with the Tories on 42 to Labour's 39, has got splashy airplay, and that's what matters. The numbers rest on highly optimistic assumptions about how many young people, who strongly favour Labour, are going to vote. But no publicity is bad publicity. YouGov's business goes well beyond political polling, and election campaigns help to flog it.

What would one predict on the basis of all this? That firms like YouGov will tend to underestimate the Tory vote. Rivers and Lauderdale are both scientists of a sort: they're trained in political science – a discipline which, as the late Ben Barber once said, avoids politics while failing to achieve science.


  • 2 June 2017 at 6:36pm
    kassia says:
    I used to say that poly sigh was like Spanish moss - neither Spanish nor moss - but the Barber barb travels better.

  • 2 June 2017 at 6:50pm
    Simon Wood says:
    Many people have been wondering about polls and how they affect big votes, so let's be clear on this: YouGov's polls are not rigged, obviously, but the firm is run by the Conservative MP for Stratford-on-Avon and a chap called Shakespeare who once ran for the Conservatives in Colchester.

    “A politician… one that would circumvent God,” Hamlet said. There would certainly be something rotten in the state of Denmark, or fishy, if YouGove attempted subliminally or by sleight of hand to stampede people into voting Conservative.

  • 2 June 2017 at 8:09pm
    IPFreely says:
    The factor that the pollsters always have to ignore is the Cretan factor. They all believe that a proportion of the voters lie to the pollsters but nobody has yet worked out a formula to compensate for the mendacious minority. Wouldn't be a bad idea to prohibit polling in the week before the election but in the land of fulfilling prophecies they would be all sent back to doing TV rating calls and we don't want that do we?

  • 3 June 2017 at 7:03am
    Joe Morison says:
    What worries most about Corbyn becoming PM is that the Tories will then blame the inevitable Brexit disaster not on Brexit itself but Labour's handling of the negotiations.

    The best result I can imagine is a Tory minority government (led by somebody competent after May is booted out in ignominy) which was unable to pass any legislation without cross party support. Perhaps then those sane MPs (still a majority) could try and rescue something from this debacle.

  • 3 June 2017 at 9:03am
    tenyards says:
    The reason the polls always underestimate the Tory vote is that they are unable to predict the affect of exposure to the right wing propaganda, dished out by our newspapers, on the voter not much interested in politics, people who often declare themselves, undecided. Currently, the circulation of right wing newspapers in the UK is six times larger than the circulation of non-right wing newspapers and repeated academic research shows a massive pro-Tory and anti-Labour bias
    If only one in twenty of the population wake up on polling day with little idea of how to vote, then the chances are high that after years of right-wing propaganda worming into their sub-conscious that they will end-up voting Tory for reasons they barely understand themselves. On the other hand it is equally likely that some traditional Labour voters who read the Sun, let us say, and many do, may not be motivated to vote on polling day.
    Interestingly, total newspaper consumption has suffered a major decline in the last seven years. Maybe in another five years it will have withered away sufficient to be a great benefit to our democracy.

  • 3 June 2017 at 12:00pm
    watwit says:
    Today a fine example of "right wing propaganda' by Erlanger at

    Strange that the "London bureau chief" of the NYTimes shd be so partisan and/or ill informed.

    • 5 June 2017 at 9:00am
      stockwelljonny says: @ watwit
      I wouldn't call that article right wing propaganda. Not exactly the Mail or the Telegraph. Seemed to be fairly reasonable and considered, well researched piece. There are obviously various machinations in the party and its not propaganda to speak about these.

    • 7 June 2017 at 6:08am
      Coldish says: @ watwit
      I agree with stockwelljonny. The NYT journalist went out and asked people for their opinions and reported what he heard. He concluded that Labour would struggle to hold Northfield. You Gov suggests an increased Labour majority in that constituency, up from 6% to 10% over the Tories. By Friday we'll see who came closer to the actual outcome.

  • 4 June 2017 at 4:57am
    Sean Mullan says:
    The NYT hates leftists. It's a 'centrist' newspaper. Anything remotely left of center is suspect. Anything that's actually social democratic is Marxist.

  • 4 June 2017 at 10:24am
    Peterson_the man with no name says:
    The pollsters are starting to look like medieval astronomers: constantly adding more and more layers of complexity to their models, in an attempt to adjust for the fact that the basic premise behind them - that the sun goes around the earth, or that one can accurately predict election results by asking people how they intend to vote - is wrong. But until a Copernicus comes along with a better way of predicting elections, polls are all we've got.

  • 5 June 2017 at 2:51am
    Amateur Emigrant says:
    Although the polls may not translate into actual share of votes and certainly won't translate into actual distribution of seats, what can't be denied is the direction of travel in all of the polls since the manifestos were published. Unless you want to suggest that people are lying about voting Labour in incrementally increasing numbers week after week? In the face of the right-wing media it's a quite astonishing trend.

    What's also certain is that May would never have called an election if the polls had read the way they do now.

  • 6 June 2017 at 3:45am
    roger gathmann says:
    Polls are a mysterious business. For instance, for a year, I've heard nothing but that Corbyn is a loser. The reason is: the polls! Now Labour is rising in the polls and it turns out that is no good, cause polls naturally underestimate Tories. Those polls! I'm glad things like this are explained by people in the press who, with their degrees in statistics and their experience in the field, know all about it.

Read more