Home / Dave Brockington / Polling in the 2017 UK General Election, and Other Notes

Polling in the 2017 UK General Election, and Other Notes


This election has caught everybody off guard, including the pollsters.  The polling houses hadn’t yet decided on a common approach in response to the wreckage of the 2015 General Election. A side benefit of this for social scientists is the natural experiment playing out in the heat of the campaign.

Before we get into that, it’s useful to remember why 2015 failed so miserably (and it was miserable for those of us who worked GOTV all day on polling day from 0530 until 2200, changed our clothes and dressed up smart, affixed the red rosette, and arrived at the Guildhall for the count only to see the exit polls coming in suggesting a Conservative majority, who then went on to witness our losing of one Labour seat here in Plymouth combined with losing what we were fairly confident of a Labour pickup by only 523 votes). It wasn’t because of the “shy tory” effect that plagued British pollsters in the 1992 election (which far too many people still believe was the fault in 2015). Rather, it was a sampling / likely voter model failure:

In looking at what’s changed it’s probably best to start with what actually went wrong and what problem the pollsters are trying to solve. As all readers will know, the polls in 2015 wrongly overstated Labour support and understated the Conservatives. The BPC/MRS inquiry under Pat Sturgis concluded this was down to unrepresentative samples.

Specially, it looked as if polls had too many younger people who were too engaged and too interested in politics. The effect of this was that while in reality there was a big difference between the high turnout among old people and the low turnout among young people, among the sort of people who took part in polls this gap was too small. In short, the sort of young people who took part in polls went out and voted Labour; the sort of young people who weren’t interested and stayed at home didn’t take part in polls either.

UK Polling Report has a useful explanation of who is doing what methodologically for 2017 (the above quote is excepted from this post). This is especially critical in being able to interpret any given poll from a reasonably educated perspective, as within the last week alone we have seen the range of estimate Conservative leads from a high of 14% to a low of 3%. As I wrote on Wednesday, while the individual estimates are all over the shop floor at the moment, one thing that is solid is the shrinking Conservative lead.

At least two sources are now publishing predictive models at the constituency level. We briefly discussed the methodology of the YouGov model in the comments of Wednesday’s post (shout out to commenter Gregor Sansa for correctly predicting their use of multilevel regression and poststratification, or which I call in an old school sense hierarchical linear modelling). YouGov’s seat-level probabilities can be found here, and it’s updated daily.  Using a different methodology (the several paragraph explanation thereof isn’t geeky / detailed enough to pass judgment on the relative merits) the Britain Elects model can be found here. The two models suggest quite different results. At time of writing (0630 BST 2 June) YouGov is estimating 317 seats for the Tories (with an error band of 285 to 353 seats), while Britain Elects is going with 362 (330 to 394). Both models also have significant, indeed wildly different predictions for the specific constituency where I campaign. Of course, the quality of the predictive model is limited by the quality of the data fed into it; those of us who blithely predicted in the media last November that Clinton would win the Electoral College were undermined by the data coming out of WI, MI, and PA. Hence, while the YouGov model makes it appear that all our hard work in Plymouth Sutton & Devonport is finally paying off, in reality the YouGov model is a captive of the underlying YouGov data. Labourites need to understand that since the 2015 GE, Labour has only been even or ahead (by one point) in three out of well over 250 polls now, and all three were YouGov.  Britain Elects takes a broader view by using data from Ipsos Mori, YouGov, TNS, Panelbase, GfK, ICM, Survation, ComRes, Opinium, ORB, BMG and Lord Ashcroft, combined with data from the British Election Study. Ashcroft also has a probabilistic model here, but it’s already a week old.

Is one better than the other? We won’t know until the 9th of June.

One other, more personal / rant note about polling and the Labour Party. There is a wing of the party that harbours deep suspicion of all polling, especially (ironically) YouGov because they have / had connections with the Conservative Party. Before this election was called, in this community polls were relegated to the status of Tory Conspiracy to demonstrate how unelectable Jeremy Corbyn is thus brainwashing the mindless sheep of the electorate from the one true path. It’s entertaining to witness all the new converts to polling data when YouGov has shown our deficit narrow to 5%, then 3%. Kids (writing to the Labour Party, not the sophisticated and discerning readers of LGM of course), this instinctive rejection of, and newfound love for YouGov is called confirmation bias, and don’t do that.

Yet people still do. I was ranted at, defriended, and blocked (I nailed the trifecta!) by a local Labour Party member (and a parliamentary candidate in the 2015GE no less) on fb yesterday because I had the temerity to point out in response to the suggestion that “we all know” polling drives public opinion that the evidence does not support that assertion (and yes, I might have pulled rank in a sense by pointing out that I used to teach survey research here, but I do have an understanding of the subject better than the average bear given that I’ve published on it). In a Labour forum on fb yesterday, it was asserted that the polling houses are under strict orders by Conservative High Command to make it appear close to scare Tories into voting given the latest YouGov poll has us only 3% behind. Apparently, when the polls show a huge Conservative lead, the fix is in to demonstrate that the LP is unelectable, when it’s close the fix is in to mobilise Conservative voters, and when the sun rises in the East the fix is in to show that the Tories are, indeed, the masters of the universe.

Conspiracy theories: for the love of God and all that is good and pure, don’t do that.

In response to some of the comments from Wednesday’s post (usually I have the time to read the comments to my posts, but lately I haven’t had the time to read the front page of LGM, let alone the comments to my own, rare, posts):

When British pollsters have failed spectacularly in a general election (e.g. 1992, 2015), it’s generally been in overestimating Labour support and underestimating Conservative support, but for different reasons (response bias / social desirability in 1992, sampling / likely voter models in 2015).

I’m not going to get into a discussion on the merits of the current Labour Party leadership at this point.  For five more days of campaigning, and a day of GOTV on polling day, we have an election to fight. I’m under no illusions that the Labour Party will be full of peace, love, and understanding form the 9th of June, but until then, at least in Plymouth, we’re doing a commendable job at party unity. While both data and anecdotal evidence suggests that around the country the post-2015 intake of members (which is a large majority of the LP’s membership, it should be stated) are proportionately less likely to do the grunt work of politics and more likely to be clicktivists, here in Plymouth we have seen a large number of new faces all working towards electing our decidedly un-Corbynista candidates to Parliament. We’ll see where we stand on the 9th of June.

jben writes: “I mean, I agree that even Corbyn and co. are the lesser evil compared to the malicious jerks who are running the country now. (I assume David also agrees, or he wouldn’t be campaigning for Labour.)”

I voted for Corbyn in 2015, and wrote about it here at LGM. The TL;DR version of that post is “not due to any sense of ideological purity, but because I think he has the best chance to lead Labour to victory in 2020”. Needless to say, that choice has been tested since, and I did not vote for him last summer. That said, I do not consider Corbyn the lesser of two evils.  I have reservations about the man, in terms of his political nous, the choices he makes in advisors, and on some bits of foreign policy, but given the binomial choice environment, I do not have one ounce of reservation that a Labour Government, a Corbyn-led Labour Government, is infinitely preferable to a Conservative government. But, given I’m active in the Plymouth Labour Party, my loyalties are also, if not predominantly, local. Local councillors, activists, and our parliamentary candidate for my constituency are also friends of mine. Over the past several elections, local and general, I’ve canvassed, plotted, attended counts, and drank with these people. I’d be doing what I’m doing regardless of the name of the party leader. I’m loyal to the party, not the leader du jour.

Ronan writes “As a matter of seats available, considering they’ve lost Scotland, what do Labour need to do to get a majority”. During the 2014 independence referendum, I wrote a series of posts, including one that explored the impact on the Labour Party if Scotland were to go its separate way. At the time, Labour held 40 or 41 seats in Scotland (this is from memory). It turns out that the Labour Party only required its Scottish bulwark once to form a government.  However, obviously, we’d take 30 or 40 seats in Scotland, as well as the political talent offered by a strong Scottish Labour Party (John Smith, Gordon Brown, to name just two).  Given we’re likely to only win one seat in Scotland (again), for Labour to get to 326 we’d have to run the table in the urban constituencies, hold if not expand in Wales, do better than predicted in the Midlands, as well as pick up seats in the South East of England. Even the optimistic (for Labour) YouGov model predicts a top estimate of 285 seats, an extra net 40 Scottish seats would get us to the precipice of an outright majority. However, that 285 represents the absolute top end of the most Labour-friendly of the various predictive models.

Finally, let’s return to the first line of this post, about how this election has caught everybody off guard. This is the first snap election in the UK since October 1974, so it’s a rare treat for anybody, let alone a politically active American political scientist, to be right in the middle of this campaign. Aside from the very occasional recall election in the US at the state or local level, there is no comparison in American politics (for better or for worse).

UPDATE: I meant to add in a completely unrelated note that two years ago today, I was at what I believe was the last ever Replacements gig at the Roundhouse in London.

  • Facebook
  • Twitter
  • Google+
  • Linkedin
  • Pinterest
  • Dr. Acula

    Any Norn Iron maps? I know they’re mostly insignificant, but I’m curious for family reasons.

    • Dave Brockington

      The only thing I’ve seen is this: http://www.belfasttelegraph.co.uk/opinion/columnists/bill-white/general-election-2017-lucidtalk-polling-plans-and-northern-ireland-seat-predictions-35652698.html And that Belfast East looks likely to go Alliance over DUP as the unionist vote is going to be split in Belfast East. But as usual, models treat NI as a static 18.

      • Richard Gadsden

        Models ignore NI because their politics is entirely decoupled from GB, so polling data from GB is completely useless for NI.

        Therefore, you’d need a completely separate set of polls and a completely separate model – but there’s only about 3% of the seats (and therefore money) in it.

        Fortunately, LucidTalk are doing exactly that. Here’s last week’s run: https://twitter.com/LucidTalk/status/869612902948511745

        One change predicted (Sinn Fein winning FST) and Belfast South and East plus South Down really tight.

        One more run on that model early next week.

        • Ronan

          Fermanagh/south Tyrone is often very close I think, isn’t it? Pretty much impossible to predict.

          • Richard Gadsden

            2001 majority 53, 2010 majority 4, 2015 majority 530 (the other way). Yeah, “often very close” is fair.

  • Great post! Thanks a lot!

  • Ronan

    Thanks for the answer to my query, Dave.

  • About Corbyn: I go back and forth.

    Not on whether to vote for Labour. That’s a rock solid given. No questions at all. But I don’t have any good sense about how a Corbyn led governement would go. The manifesto is pretty good. Corbyn himself is doing better campaigning (after a shaky start; plus May has been doing rather poorly) which is promising.

    But his track record as leader of the opposition isn’t good. The Brexit three line whip. The PLP revolt (even if you put a fair bit of blame on the never Corbyners, the mass shadow cabinet resignation shows that there’s something else going on). Trident weirdness. Etc.

    British governance seems to be going downhill (though nothing like the US’s crash). Corbyn seems more within that tradition than against it.

    That being said, much better somewhat poor governance in service of good policy than the poor everything.

    The other issue is what happens under the various loss scenarios. A narrow loss sets Corbyn up to stay on. Indeed, it would make the case that he and his group make Labour unelectable. (You’d have to argue that someone else would have won which is trickier than arguments from a catastrophic loss.)

    My optimistic “rational” scenario is that we hold the line and a uniting figure who takes the policy gains we’ve made and unites them with better leadership and a more palatable campaigner.

    • sibusisodan

      I think Abbott and McDonnell are weaknesses for any Lab front bench.

      I don’t think Corbyn’s strengths lie in parliament: he seems much more comfortable campaigning, advocating on issues and doing policy detail.

      • I don’t think Corbyn’s strengths lie in parliament:

        Something of a problem for someone aiming to be PM!

        he seems much more comfortable campaigning, advocating on issues and doing policy detail.

        Yes…but he’s not particularly good on any of these. The current campaign and manifesto success pushes me to reassess his campaigning and policy skill, but it’s mostly me pushing against the risk of confirmation bias.

    • Donalbain

      This is the first election where I haven’t even considered voting Labour. I cannot bring myself to vote for a pro Brexit Prime Minister.

      • humanoid.panda

        You ought to read this blog, and think about the folly of deal breakers. And even on Brexit- Labor still beats alternative.

      • I urge you to reconsider unless you are in a constituency where not voting for Labour doesn’t matter. Even then I urge you to reconsider.

        I mean, I share your rage about Brexit and Corbyn’s ongoing suck on it. But there’s something of a sunk cost there. Plus, a Labour upset would open up a pull back even against Corbyn’s deep desires (or at least a Norway style deal).

        Lots of people say that a May triumph would make for a better Brexit, but I’m rather skeptical about that.

        • Murc

          Plus, a Labour upset would open up a pull back even against Corbyn’s deep desires (or at least a Norway style deal).

          Is it wrong that I worry that Labour wins, negotiates a Norway style deal, and the Tories and further-right UKIP nutjobs spin a dolchstoss narrative out of it? “We voted for Brexit, but instead we have to still obey all the rules of the perfidious wogs AND we don’t get a say in making them anymore! Labour has left us in a worse position than where we started from!”

          • sibusisodan

            Not at all!

            Please also don’t neglect to worry that the economic effects of Brexit taking place under a Labour govt would be blamed on the incumbents, irrespective of the political messaging around the final deal!

            • Murc

              Well, I mean, that’s basically why we’re having this election now, right? May would rather the next election, the one after this, take place three years after Brexit rather than one year so that the economic whammy isn’t so closely tied to her party.

              • It’s hard to say! That would be a sufficient reason, but it’s not at all clear that it was May’s reason. Given that was a surprise, as in contrary to all her claims before that, it’s really unclear. The wanting a better situation for her negotiations seems as likely. Or a mix.

          • Is it wrong that I worry that Labour wins…the Tories and further-right UKIP nutjobs spin a dolchstoss narrative out of it?

            That’s it. Labour wins and the dolchstoss stuff begins.

            How effective it will be is open. It’s possible that the rabid Brexiters will end up on the back foot.

            One thing to remember is that Brexit wasn’t a groundswell and the current support contains a big chunk of resignation. Cameron took a bad gamble to shut down the Brexiters. With a weak Labour campaign, we barely lost. With a stronger Labour or a generally more effective counter campaign (or just a better crafted referendum) we could have won.

            We now have a bad status quo bias, and the Brexitters surely have strength. But they are also pretty obviously clowns, liars, and nasty people. It hurts them.

            ETA: Don’t get me wrong. It would be probably be brutal. But it’s not necessarily hopeless.

          • djw

            This worry seems like a specific example of a more general truth–whomever is in charge for Brexit, the other party will forcefully criticize how they manage it and accuse them of screwing it up and doing real damage to British interests.

        • sibusisodan

          I can’t see how more Tory mps makes for a better Brexit given the sheer weakness of Tory Europhiles right now. It would be nice, but unrealistic.

          I’m in a safe Tory seat. My rationale for Labour runs thusly: I’m voting for a representative government, not directly for PM.

          A Labour government, a Labour cabinet governing by collective responsibility, would – given the proEU makeup of the PLP – deliver much better Brexit outcomes than a Tory govt.

          Those Brexit outcomes will still be awful, but I’ll take what I can get.

          The personal policy preferences of the PM aren’t determinative of the government’s policy.

          • The reasoning is that the narrowness of her majority strengthens the hard Brexit voices. No Conservative government will be anti Brexit, but there’s room for a softer Brexit, I think. The continental view is that having a more personal mandate will give her both vote and standing to go for a better deal and back off the nihilist crap.

            Meh. You could argue that a weak win is a rejection of the hardline brexit view.

            The bit I’m not convinced of is that May isn’t hard brexit herself, now.

            • sibusisodan

              Yeah, its the rhetoric gap where it falls down for me.

              May’s electoral pitch revolves around an unspoken hard Brexit. That will feed in to the expectations of her MPs as well as the electorate.

              Given that the entire Brexit farrago is driven by a domestic internal Tory party dispute which got a little out of hand, electing more Tories without resolving the underlying dispute will not moderate those forces.

            • ericblair

              At this point it’s hard to tell what part of the UK Brexit position is Trump-esque bluster, what part is political necessity, and what part is some deluded sense of superiority over the benighted wogs.

              I’m watching this from the Continent and am a career staff weenie. The EU has its shit together. The UK does not. Even if the UK came back with some half-reasonable negotiating framework that would be acceptable in principle, the amount of staff work to get to some coherent policy state before the clock runs out is mindboggling. And, of course, the UK government is not resourced to do it.

              So, unless it ends up as a Norway Brexit-in-name-only ctrl-C ctrl-V job, it’s going to be chaos in two years and the government’s going to be holding the bag. I don’t think a majority government of either party would have the gonads to declare failure and un-Brexit by itself. Maybe a narrow majority or coalition, with enough MP defections once the failure stink starts to rise, may force some sort of political realignment and create a way to flop out of this folly.

              I don’t know. 2016 was the year of madness, and everyone’s going to be paying for it for a long time.

              • No one serious was pro-Brexit. Ever.

                No policy papers were developed. Etc.

                The clowns won and we’re going to pay.

                • sibusisodan

                  The faces of Gove and Johnson the morning after made that very clear indeed.

              • Richard Gadsden

                The serious answer is:

                Norway option as an interim. Work something out properly over a ten to fifteen year period to make it work. You can negotiate treaties with third countries over that period as well.

                Blame Cameron for not doing the prep work so it takes so long.

                • Murc

                  The problem with the Norway option, from the Tory point of view, is that it will empower the nativists they hoped to neuter with the referendum.

                  The only reason Cameron agree to the referendum to begin with was to protect his right flank from UKIP and friends, which had started to assemble enough vote share to be genuinely scary to the Tories in a number of ways.

                  If you go with the Norway option, which is, from the perspective of the racists, a much worse deal than just being in the EU, there’ll be hell to pay. Labour doesn’t give a shit about those guys, they’re never gonna vote for’em anyway, but the Tories have a real concern.

                • Richard Gadsden

                  The political argument, if they’d set it up over the last nine months, would be that Cameron had left such a shambles that they couldn’t leave properly. So they’ve done this as a mark of faith, so Britain is actually outside and couldn’t be taken back in by Labour without a referendum. And then they can do all the work now that Cameron should have been doing in 2010 and once we’re ready to go it alone, we’ll do that.

                  They can say “we need a free trade agreement with American and China and India and with the EU. Once we have those, we’ll leave the EEA. But that will depend on how fast the Americans and Chinese and Indians want to talk, not just on us – let’s not get tied into a two-year timetable created by Eurocrats to screw us up.”

          • Murc

            My rationale for Labour runs thusly: I’m voting for a representative government, not directly for PM.

            I would submit that from my perspective a very real issue in the UK is that the position of Prime Minister has become increasingly more powerful and presidential-ish over the years, making important decisions that parliament not only doesn’t review closely but often isn’t even aware of.

            I understand that Westminster systems aren’t set up to deal with divided government at all, but it seems to me like the more strong-executive a system is, the less justification there is for that executive to not be elected directly.

            I am not proposing any specific reforms to the UK. I am just thinking out loud here.

            • I would submit that from my perspective a very real issue in the UK is that the position of Prime Minister has become increasingly more powerful and presidential-ish over the years, making important decisions that parliament not only doesn’t review closely but often isn’t even aware of.

              The May government has been accelerating this, big time.

              This is why they fought (to the supreme court!) a vote on triggering Art 50 (which they won handily so wtf). This why the great repeal bill is being set up so ministers can “rewrite out” the EU references…and more!

              It’s pretty bad.

            • sibusisodan

              Oh, the developments towards a quasi-Presidential PM under Blair and Cameron are not good at all.

              But the trend of taking power out of the hands of Parliament is more general, and results in more power in the hands of the Cabinet overall, not the PM alone.

              There’s been quite an increase in using Statutory Instruments – blank sheets for the relevant Minister – to do stuff instead of Parliamentary primary legislation. I think this has happened with Health quite a lot.

              But Parliament has to agree to that! They could decide not to.

              • hypersphericalcow

                > But Parliament has to agree to that! They could decide not to.

                This seems analogous to the US Congress ceding almost all foreign policy decisions to the White House over the last few decades. They get to complain all they want, but don’t actually have to make any decisions.

      • Murc

        This is the first election where I haven’t even considered voting Labour. I cannot bring myself to vote for a pro Brexit Prime Minister.

        And yet, you have just stated your intention to vote for May. Curious.

        • Weirdly, there are places in the UK where you can not vote for Labour and not even half vote for the Conservatives: Any constituency where the battle is LibDem vs. Conservative and the Labour candidate isn’t remotely competitive.

          It’s more common than one might think.

          (This is aside from safe seats. There are competitive marginal seats where Labour is the effective third party.)

          • Richard Gadsden

            Weirdly, there are places in the UK where you can not vote for Labour and not even half vote for the Conservatives: Any constituency where the battle is LibDem vs. Conservative and the Labour candidate isn’t remotely competitive.

            More than those (and that’s 50-odd, just counting the ones which had LD MPs elected in 2010 or 2005). There’s Scotland, where the anti-Conservative choice is more likely to be SNP (and 40+ seats have no chance of a Tory at all). There’s Brighton Pavilion, where it’s Green. There are a few seats in Wales where Plaid Cymru are competitive. And there’s Northern Ireland, where Labour doesn’t have candidates and the Conservatives have negligible numbers of votes.

            There are also 100-150 or so seats in England and Wales where the Conservatives have no chance. About a dozen are seriously competitive between Labour and the Lib Dems (the ones which had Lib Dem MPs before 2015, plus Vauxhall), one, Bristol West, is a three-way contest between Labour, Lib Dem and Green and one, Ceredigion, is a Lib Dem – Plaid Cymru contest.

            Finally, of course, there’s Buckingham, where I recommend spoiling your ballot paper because the “Speaker seeking re-election” is a completely ludicrous prospect, as all the main parties stand down and you just have a bunch of mad independents.

            • Great points.

              • Richard Gadsden

                I am somewhat biased on this – I’m a Lib Dem parliamentary candidate.

                • Good luck!

                • Richard Gadsden

                  Thanks. I got 2.1% last time, so I’m not really expecting much!

        • Donalbain

          Your computer send to be malfunctioning. Your screen is displaying words that were never actually typed.

    • mongolia

      have a question related to a potential PM corbyn: if he does a terrible job as pm, and runs an unpopular, scandal-filled prime-ministership (is that a word?), would there be a way that labour mp’s could call, say, a vote of no confidence, and then do a massive party membership drive to get the kinds of high turnout that may actually remove him from his leadership position? obviously a bit harebrained, but is this possible in theory, and potentially as a way of swaying soft labour votes who can’t bring themselves to vote tory but are anywhere from concerned to disgusted by corbyn?

      • Murc

        A no confidence vote in parliament triggers another election, is my understanding. I don’t know if there’s a way for a party to remove their sitting PM who won’t step down or resign without doing the full no-confidence thing, tho.

      • I don’t think this is feasible.

        Putting aside the technical issues (e.g., does no confidence trigger an election), Corbyn has a pretty strong lock on the membership. It’s hard to say what would change that exactly.

        I don’t think it would sway soft Labour voters to say “Hey, after he implodes we, who were unable to get rid of him before, will get rid of him!”

      • sibusisodan

        The PLP can trigger a party leadership election without going the full no confidence route.

        It would end up in much the same way as previous attempts though.

        ETA: this is a major plot point in Frederick Forsyth’s The Fourth Protocol, to change Labour leader without a General Election, although the voting procedure has changed.

        • Ronan

          “this is a major plot point in Frederick Forsyth’s The Fourth Protocol, to change Labour leader without a General Election, although the voting procedure has changed.”

          I like you sibusisodan, so I mean this with all due respect. But this sounds like one of the most most boring plotlines imaginable.

          • Richard Gadsden

            Well, the other main plotline in that novel is a backpack nuke, so there’s plenty of excitement to be had.

            Also, have you ever watched an Australian leadership spill? If not, set up a google alert and read a liveblog next time one happens – they seem to be every couple of years.

          • sibusisodan

            If I tell you that Ken Livingstone is the one lined up to be the new Labour leader, to enact a Marxist program, I’m sure you can’t help but change your mind.

  • msdc

    The left has a serious problem with magical thinking and epistemic closure on both sides of the Atlantic.

    • Mrs Tilton

      It certainly does! And that problem is called “the Right”.

It is main inner container footer text