It’s the eve of the referendum, so we have a flurry of late polls. Later on this evening we will have figures from ComRes and YouGov (Ipsos MORI’s final poll is normally in the Standard, so will probably be out tomorrow morning), already we have final figures from TNS and Opinium.

Opinium have topline figures of REMAIN 44%, LEAVE 45%, Undecided 9%. Leave are ahead by the tiniest of margins, but clearly the two sides are within the margin of error of each other. Full tabs are here.

TNS‘s final referendum poll also has Leave ahead, this time by two points. Topline figures here are REMAIN 41%, LEAVE 43%, Undecided or won’t vote 16%. Note that unlike TNS’s last few polls their headline figures here are NOT weighted for turnout – with their turnout model they would have been Remain 42%, Leave 49%. Full tabs are here.

I will update later once ComRes and YouGov publish. In the meantime both of the non-British Polling Council companies who produced more unorthodox polls last week have produced updated figures – SurveyMonkey have final figures of REMAIN 50%, LEAVE 47%; Qriously (the company sampling via smartphone ads) has final figures of REMAIN 37%, LEAVE 51, Don’t know 12%. Again, make of that what you will.

UPDATE: The ComRes and YouGov eve-of-referendum polls are now also out. Whereas TNS and Opinium both had Leave leads, ComRes and YouGov both show Remain ahead (albeit, by different margins):

ComRes for the Daily Mail have topline figures of REMAIN 54%, LEAVE 46%, a widening of the Remain lead after their last poll showing Remain and Leave within a point of each other. ComRes have reallocated don’t knows based on respondents’ views of the impact of Brexit on the economy, which looks like it boosted Remain by a point or so. Full tabs are here.

YouGov for the Times have topline figures of REMAIN 51%, LEAVE 49% – so considerably closer. The YouGov poll now includes a turnout weight (though it made no difference at all to the topline) and a squeeze question, which also bumped Remain up by a point. Full tables are here. On YouGov’s website they’ve also updated the multilevel regression and post-stratification (MRP) model of referendum voting using all their data, which they first posted earlier in the week, that is now also pointing towards a small lead for Remain.

Note that all four of the polls here include Northern Ireland. Most general election polls don’t, and so polls during the EU campaign have varied on whether they do or do not include NI – all these four do.

UPDATE2: Two more polls published on the day itself. Note that these polls were conducted before polls opened, they are only published today. It’s illegal to publish polls conducted on the day until polls close, but perfectly fine to publish polls conducted before polls opened.

Ipsos MORI‘s final poll has topline figures of REMAIN 52%, LEAVE 48%, putting Remain back ahead after a leave lead in MORI’s penultimate poll. MORI have slightly changed their turnout filter for their final poll, basing it on how likely people say they are to vote and how important they say the result is to them. Full tabs are here.

Finally, and a little surprisingly, Populus have produced a final call poll. Populus’s Andrew Cooper has been working with the StrongerIn campaign so the company haven’t been putting out regular polls during the campaign, but they have produced final topline figures of REMAIN 55%, LEAVE 45%. Unexpectedly given the topline results the poll was conducted online (completely messing up that “phone & YouGov saying in, other online saying out” pattern). Populus haven’t released tables yet, so I’ve no details of the weightings or adjustments used.

1,842 Responses to “Eve-of-Referendum polling”

1 2 3 4 37
  1. We already know there was a suppression of people saying they would vote Leave in the days after the murder. We’ve seen that with polls already.

    We’ve also seen a much closer race, or Leave ahead, in slightly more recent fieldwork.

    So a poll with 5 day old fieldwork is of limited value in a fast moving campaign.

  2. I think Remain will win with 52%

  3. YouGov encouraging too with a swing back to Remain.

  4. Personally I can cope with any result. I have homes in three countries and could go for French or Spanish citizenship if I had to. Not everyone has that option. I do think that the prospects of both the EU and the UK will be considerably diminished if we vote leave but for me it will be an inconvenience rather than a disaster. I do, however, struggle to see how being apart is better than working together.

    Throughout our history we have sought alliances with other European countries. Usually this meant our monarch marrying a foreign princess but that did not always end well. The problem was that we were usually seeking an alliance with one country in order to best another country. The EU is a different sort of alliance with all countries agreeing to proceed in common for the benefit of all. If we want to abandon that idea then civilization is taking a step backwards. I hope for the best but I fear the worst.

  5. @The Monk

    Rich and DRmibbles will only accept that if all the fieldwork was done today, being the 6th day after Jo Cox was brutally murdered (an event that apparently wasn’t going to affect VI anyway…)

  6. thunder and heavy rain in 7/10 top leave area’s tomorrow. Also during most busy polling times.

    God on the side of Remain? (Not being serious about that btw)

  7. I’d be happy with fieldwork from Monday onwards. We already have a bunch of polls covering the days prior.

  8. @ Chris Lane. Yep I’ve predicted 52/48 to Remain. These last two polls make me a tad more confident .

  9. Maybe we could settle it by polling the whole nation?

  10. The Last Fandango – “I am quite sceptical about big data for things like this because of the ‘observer effect’. The campaigns know that the social media stuff gets measured so they pump the ether full of retweets, likes, faves etc. from sock puppet accounts etc to try to capture a favourable measurement. But it isn’t the activity of real people. And I think it is really tough to differentiate (not impossible, but tough).”

    Well here is the Google Trends data – pretty impossible to manipulate because they get billions of searches every day, and they’re going by the search queries people freely input into their machine.

    They’ve compiled a whole bunch of graphs – search interest for Leave is way higher than for Remain. People have been asking them things like “is Russia in the EU” :-) They’ve also got their own brexit map showing which parts of the country appear to be searching for more brexity things. They’re also tracking all the politicians.

    It looks very Brexity to me.

  11. Remain should have gone for Sheila Hancock as leader from the start – would have been a landslide

    As it is I’m sticking with 55%-45% in favour of remain – I think the economic worries will creep back into people’s minds.

    I think the global view that Hancock expressed and that RMJ has put very well should be the deciding factor in favour of a remain vote, but I fear it has been swamped in the scare/bully tactics and mishandling by the Remain campaign.

  12. BBC still managing to lead the news with Jo Cox..

  13. Sam Coates of the Times saying that the YG poll includes NI.

    Can we now expect YG to start polling the UK (thus justifying Anthony’s blog title) instead of YG?

    Then the Northern Irish can ask damn fool irrelevant questions about English only matters, just as the Welsh and Scots have to suffer?

  14. EU referendum poll:
    Remain: 51% (+2)
    Leave: 49% (-2)
    (via YouGov, online / 20 – 22 Jun)
    Excludes DKs.

  15. Candy, but you also said Bing made the call 55/45 on their engine algorithm. What have Google called?!

    Long term, Leave have done badly, back in 2013, leave were on 46, stay on 30. Britain is eurosceptic, only 1/4 are happy with the EU work. But Leave haven’t done as well on this as they’d hoped.

  16. I am honestly just sensing a huge shock. All we can do is wait and see now.

  17. EU referendum poll:
    Remain: 48% (+2)
    Leave: 42% (-3)
    (via ComRes, phone / 17 – 22 Jun)

  18. Heather

    Good weather forecast for Scotland. (though as John Curtice has pointed out, the weather makes little/no difference to turnout)

  19. How much do people think older voters will be influenced by family considerations?

    If you ask my mother her VI as a straight question she says ‘out’. But she has voted ‘in’ by post saying she did it for her grandkids. Bizarrely she still says she is an ‘out’er’….

    How do you cater for that in a poll? You cant.

    That’s one anecdotal reason for why I think the pollsters can have NFI as to what the result will really be.

    Btw, one of the interesting things in this ref vs Quebec 95 is that the question here is very stark.

    The Quebec question was much more ambiguous:

    “Do you agree that Quebec should become sovereign after having made a formal offer to Canada for a new economic and political partnership within the scope of the bill respecting the future of Quebec and of the agreement signed on June 12, 1995?”

    As a Quebecker you got potentially two more bites of the cherry. One because a new partnership might have been agreed and two because it was left deliberately ambiguous as to what ‘sovereign’ meant – it did not necessarily mean independent (and they deliberately avoided that word). There was this weird half way house idea of ‘sovereignty association’.

    Here it is (deliberately) stay or go, no ambiguity or nuance.

    I wonder how that will drive emotions in the ballot box.

  20. Yougov remain 51 leave 49

  21. “Wasn’t the sovereignty of the Westminster Parliament to do exactly as it wants (as long as the 800+ unelected ones go along with the Commons) exactly what you have been campaigning for?”
    @oldnat June 22nd, 2016 at 9:55 pm

    Now now, don’t sully the argument by pointing out the UK’s democratic deficit. (BTW, you forgot to mention the qangos. :-)

  22. We’ve seen that with polls already.

    Not really. The clutch of polls with the bump for remain over the weekend were mostly completed before the murder. I don’t think there’s any robust evidence that pro-leave sentiments were suppressed in polling conducted in the period since.

  23. I went out canvassing for REMAIN again today with a team made up mainly of Lib Dems but also a Green and some from no party. I found more REMAINS than LEAVES as expected in the Lib Dem area we were in. At odds with my expectations I found a few shy remainers. People would say they had not decided, then ask who I was representing, then clearly relax and say they were for REMAIN.

  24. @DSL

    Bing said 55/44 to Remain on 13th June. Can’t get it to work to give prediction as of today. Hopefully it’ll work tomorrow!

  25. @Candy

    All very interesting re Google but (A) social media can and is regularly manipulated (Google do it themselves!) and (B) I note Google haven’t given us a prediction result. Now why do you think that might be?

    Btw it is fairly well know that there is a massive Leaver social media spin operation.

    Rich, if you are so confident you should put your money where your mouth is. Otherwise it’s just Mystic Meggery.

  26. @CANDY

    I seem to recall a similar thing was done before the general election which correctly predicted a Tory win. But this is little better than clairvoyance – they get some right and others crushingly wrong.

    Take this one for example:

  27. When you say Comres distributed DKs based on view of the economy, do you mean Comres’s view of the economy, or that of the DKs?

  28. I still cannot believe the MSM is talking about the line at the bookies when they got is so spectacularly wrong at the general election AND have a vested interest in having people bet on the wrong outcome.

  29. I prefer to rely on the bookmakers – after all when it comes to money they are pretty much experts. They have sophisticated computer software to work out all the required prognostications.

    Looking at Oddschecker right now I see that bets are 56.86% for remain and 43.14% for leave. Best odds are 3/10 for remain and 10/3 for leave. Still tight but remain slight favourites.


    Quite – Dr Mibbles only really likes polls that show leave in the lead, everything else flawed or dated or something else wrong with them. I suppose most of us have our biases – myself included – but some don’t even try to be even handed. Given evidence my guesstimate – and that is all it can be – would be 52/48 for remain. But who knows….

  31. Am I the only one who thinks the polling companies pick a figure then work out how to get there?

  32. New predictions added:


    Exactly, they are experts. On money. Not prediction or polling. All you get by looking at the bookies is a perception of what most people think will happen, which isn’t the same as what will happen – but it can often coincide. You’re better off following the polls to be honest.

  33. It’s all over….

    The psychic octopus has plumped for Remain!

    Doubtless the psychic octopus is owned by Goldman Sachs…

  34. @Candy, if Google wish to make a call based on their traffic so be it. Bing clearly have based on traffic, polls, bettting movements, the kitchen sink etc. They chuck the lot in the mixer. To be fair, they got the Scots Ref right. I can’t get it to work either, so hopefully an update is coming.

    If there is a late swing to Remain it will correlate with folk talking about remain in the last few days I’ve noticed at school + posters appearing. If the soft eurosceptics are backing remain, this won’t surprise me

    Between May 2013 and now, Leave have gained +3% to 49, while Remain have gained +21%. The hard eurosceptics haven’t budged but this does mean that Leave have lost nearly all the soft eurosceptics out there. Old people are on pensions, they don’t need to worry about jobs. The rest of the voting public do and that’s why I think Remain have eaten all the don’t knows from 2013 to now. I don’t like brushing my teeth, but it’s good for me.

  35. @The Last Fandango

    You know that the Google Trends thing is purely search results, right?

    Google haven’t gotten into the prediction game though they might in the future, they just present their trends without comment.

    So far from the big data people we have:

    Equimedia (who got the Scottish referendum right but the GE wrong):

    They are showing 44%, Leave on 43% and undecideds on 13% – they predict the undecideds will break for Remain. They use Facebook, Twitter, Instagram and Youtube.

    Then we have the following tool developed by Professor Massimo Poesio and Professor Udo Kruschwitz of the University of Essex:

    It is showing Leave ahead, but only marginally, and for most of the campaign Remain was ahead, but slightly.

    And then we have Bing Predicts, which showed 55/44 to remain on 13 June. Nore sure what it is currently.

    So as up in the air as the opinion pollsters!

  36. @RELICK

    Remain leading 15-7 at present. Mind you, it’s all crystal ball gazing.

  37. Is anyone doing a callback poll to see how people voted tomorrow (a la YG after indyref)?

  38. Matt,
    Yes I am waiting to hear Dr Mibbles on the latest YouGov poll, which is almost identical to the one they took during his “irrelevant to anything” period.

    I don’t trust any of them anyway…

  39. ComRes suggests 78% turnout. Interesting as Electoral Commission told authorities to prep for 80%.

    Think that is high But still think it will get over 70%.

  40. @The Last Fandango

    Sadly the poor psychic octopus died!

    A great blow to all those who loved his predictions! :-)

  41. @Candy

    “You know that the Google Trends thing is purely search results, right?”

    Yep. You know organisations pump search terms into Google to drive results on Google Trends, right?

    Even my barber shop does it!

  42. Great to see NI being included in these last 4 polls.

    We exist!

  43. BazInWales (and others mentioning people reluctant to identify their stance).

    I suspect that would not be unusual in a campaign that is “divisive” [1] or at least portrayed by the media in that way.

    AFAIK no one has replicated the Survation poll commissioned by the Daily Express in March 2014, when they asked –

    “Over the past 3 years, have you, at any point, received threats or abuse from other people as a result of differing views on the issue of Scottish independence”

    7% said Yes – on the internet : 8% said – Yes – in person : 87% said No.

    12% said ” I am afraid to express my views on the issue of
    Scottish independence due to fear of being threatened, abused or shouted down by those of opposing views”

    The gender gap on that seems unsurprising (14% Female : 10% men – Neil A’s wife?)

    Yes supporters reported more abuse than Noes –

    15% of Yessers said Yes – on the internet : 11% said – Yes – in person : 79% said No.

    2% of Noes said Yes – on the internet : 7% said – Yes – in person : 92% said No.

    It would be interesting to see a similar investigation into this referendum, instead of assumptions being made.

    [1] Serious political decisions ARE divisive! What else would people expect?

  44. Prof Howard

    “We exist”

    Therefore, you think?

  45. I’ll post again once the picture starts to emerge. Honestly thinks it going to be Leave by at least 3-4 points. Am I on my own here. We shall see!

  46. ProfHoward, and now you are included, Remain have a lead, just as I predicted, NI is worth 2%.

  47. @Candy

    That was Paul the Octopus. He has been replaced by Otto. Apparently.

    I am unclear whether the methodology is any better however.

  48. @RICH

    “In the event of a Leave vote, could the parliament simply refuse to implement it based on the MPs in the chamber? I know that would make us a bit like Zimbabwe or North Korea, but just wondered. Is this a real possibility?”

    Interesting question. Parliament is sovereign according to the British constitution, which means that parliament has the final say on legislation or any constitutional change. Referendums are not necessary or binding according to UK law. They are NOT part of the democratic process under British law and do not form part of our political tradition. The first ever referendum in the UK was, ironically, the one to decide Common Market membership back in 1975.

    Can parliament block any ratification of the referendum result? Yes of course. Will it do so? Highly unlikely, unless there are a sufficient number of MPs who feel they have to do so to save the country from a national disaster. In the case of a leave vote this is very much an unanswered question – no MP would ever admit to want to do this, for obvious reasons! However, in extreme circumstances (and it is debatable what extreme means) MPs can definitely refuse to accept a referendum result. Such as situation would undoubtedly cause a constitutional crisis and involve the Queen to make a final decision. This is a nightmare scenario that the Queen has dreaded ever since becoming the monarch in 1952, as it would make her responsible for a decision that will affect the nation for decades to come.

    We live in interesting times…….

1 2 3 4 37