I hope most of my regular readers would assume a Daily Express headline about a “poll” showing 80% of people want to leave the EU was nonsense anyway, but it’s a new year, a new election campaign, and it’s probably worth writing again about why these things are worthless and misleading as measures of public opinion. If nothing else, it will give people an explanation to point rather overexcited people on Twitter towards.

The Express headline is “80% want to quit the EU, Biggest poll in 40 years boosts Daily Express crusade”. This doesn’t actually refer to a sampled and weighted opinion poll, but to a campaign run by two Tory MPs (Peter Bone and Philip Hollobone) and a Tory candidate (Thomas Pursglove) consisting of them delivering their own ballot papers to houses in their constituencies. They apparently got about 14,000 responses, which is impressive as a campaigning exercise, but doesn’t suddenly make it a meaningful measure of public opinion.

Polls are meaningful only to the extent that they are representative of the wider public – if they contain the correct proportions of people of different ages, of men and women, of different social classes and incomes and from different parts of the country as the population as a whole then we hope they should also hold the same views of the population as a whole. Just getting a lot of people to take part does not in any way guarantee that the balance of people who end up taking the poll will be representative.

I expect lots of people who aren’t familiar with how polling works will see a claim like this, see that 14,000 took part, and think it must therefore be meaningful (in the same way, a naive criticism of polls is often that they only interview 1000 people). The best example of why this doesn’t work was the polling for the 1936 Presidential election in the USA, which heralded modern polling and tested big sample sizes to destruction. Back then the most well known poll was that done by a magazine, the Literary Digest. The Literary Digest too sent out ballot papers to as many people as it could – it sent them to its subscribers, to other subscription lists, to everyone in the phone directory, to everyone with a car, etc, etc. In 1936 it sent out 10 million ballot papers and received two point four million responses. Based on these replies, they confidently predicted that the Republican candidate Alf Landon would win the election. Meanwhile the then little known George Gallup interviewed just a few thousand people, but using proper demographic quotas to get a sample that was representative of the American public. Gallup’s data predicted a landslide win for the Democrat candidate Franklin D Roosevelt. Gallup was of course right, the Literary Digest embarrassingly wrong. The reason was that the Literary Digest’s huge sample of 2.4 million was drawn from the sort of people who had telephones, cars and magazine subscriptions and, in depression era America, these people voted Republican.

Coming back to the Express’s “poll”, a campaign about leaving Europe run by three Tory election candidates in the East Midlands is likely to largely be responded to by Conservative sympathisers with strong views about Europe, hence the result. Luckily we have lots of properly conducted polls that are sampled and weighted to be representative of whole British public and they consistently show a different picture. There are some differences between different companies – YouGov ask it a couple of time a month and find support for leaving the EU varying between 37% and 44%, Survation asked a couple of months ago and found support for leaving at 47%, Opinium have shown it as high as 48%. For those still entranced by large sample sizes, Lord Ashcroft did a poll of 20,000 people on the subject of Europe last year (strangely larger than the Express’s “largest poll for 40 years”!) and found people splitting down the middle 41% stay – 41% leave.

And that’s about where we are – there’s some difference between different pollsters, but the broad picture is that the British public are NOT overwhelmingly in favour of leaving the EU, they are pretty evenly divided over whether to stay in the European Union or not.


220 Responses to “No, polling doesn’t show 80% of people want to leave the EU”

1 2 3 5
  1. Thank you Anthony. When I saw it was the Daily Express I was surprised the proportion wasn’t higher, given their propensity to do self-selecting, premium rate “polls” with questions like “Should we keep giving away billions in free money to evil terrorists?”

  2. “Daily Express in outrageous shocking revelation” shocker!

  3. I’m quite surprised they haven’t had a “crusade” to restart the Crusades yet.

  4. To the contrary of the Express’ spin, I think it might be worrying for Kippers (and Tory “Better Off Outers”) that as many as 20% of the people likely to respond to Tory canvassing in the East Midlands want to stay in the EU.

  5. It would be interesting if some of the polling orgs could test people’s actual knowledge of the things they have opinions on.

  6. “I hope most of my regular readers would assume a Daily Express headline about a “poll” showing 80% of people want to leave the EU was nonsense anyway”
    ____

    I think the fact that none or at least very few of us discussed the Express poll would back this up.

    And shouldn’t there be rules regarding such polls like proper demographic Weighting etc? You know (Precision Polling).

    However….Surely the UK’s membership within the EU in it;s current form needs addressing!!

  7. Interesting, but not particularly useful. Many millions of people enter polling booths uninformed. You can’t sample for knowledge of issues or the result will quite simply be wrong.

    The most uninformed idiot could affect the makeup of the government – but MPs have to represent uninformed idiots as well.

  8. NICK NAME

    “It would be interesting if some of the polling orgs could test people’s actual knowledge of the things they have opinions on”
    ___

    I rather suspect the people requesting the polls in the first place would not like the findings if that was to happen.

  9. BBC Radio 2 this morning seemed convinced enough to report the 80% figure, unfortunately. More fool them.

  10. ok now run a survey to get 80% in favour.

  11. Even if there was a referendum, which I don’t think will happen as Tories won’t win, UK will definitely stay in EU.

    Why? People don’t want change into the unknown. Yes campaign is silent, no campaign is always active and still can’t get a majority. Also, EU nationals in UK, and British in EU will vote to stay also. Millions of votes here.

    It seems to me this referendum is just smoke and mirrors, instead of solving some real problems that exist.

    If instead of threatening, Tories would work with other countries, they could get some change that is needed, and is smth other countries want.

  12. Miliband says he wants the Inquiry published. Interesting – I suspect he sees being open and honest about it as less harmful than being seen to be dodging it.

  13. The inquiry was big gordies revenge on tony blair-he responds by “supporting ” EM and mandelson and clarke dis the mansion tax.

    One day labour will move on from the TBGBs.

  14. Search for Opinion Polls Yes Prime Minister on a well know video sharing site- Sir Humphrey explains just how they work

  15. I think Jim Murphy has a real cheek going to Dundee. Who does he think he is?

  16. Syzygy,

    Apart from competition law, one of the practical things about renationalising the railways is that they would require a lot of capital to run. Since the public don’t like the government raising money, this is a big problem. There’s no point having a railway if you can’t invest in it.

    I suspect this is the main reason Ed B is wary of renationalisation and would rather leave it as an option rather than a commitment.

  17. Crikey now you can see where and how the quote quote “monotonous Scottish” stuff manifests from.

    Don’t blame the Scots.

  18. “Just getting a lot of people to take part does not in any way guarantee that the balance of people who end up taking the poll will be representative.”
    Council elections with 20% turnout?
    Is it that the 80% who then don’t vote really don’t care, or that they can’t be bothered to go to spoil their ballot papers with ‘none of the above’?

    ” YouGov ask it a couple of time a month and find support for leaving the EU varying between 37% and 44%, ” and 16% or so ‘don’t know’ but might well be swayed by a ‘poll’ saying 80% want to leave.

    But the YouGov EU poll has some fascinating sidelights:
    During 2014 the ‘Remain IN’ had an average and fairly steady 1% lead.
    Prior to 2014, there was a consistent small majority for leaving.

    But “Imagine the British government under David Cameron renegotiated our relationship with Europe and said that Britain’s interests were now protected, and David Cameron recommended that Britain remain a member of the European Union on the new terms.” produced a ‘Remain IN’ lead of about 30%. with don’t knows and won’t votes about the same.
    That means 15% of those polled would believe DC apparently without evidence or consideration of any evidence and change their stance.

    I note YouGov didn’t ask “Imagine the British government renegotiated our relationship with Europe so that Britain’s interests were protected”

    That means 15% of those polled would believe DC apparently without evidence or consideration of any evidence and change their stance.

    Ho Hum

  19. it’s very boring the scottish stuff, but it does have a material impact on the election.

    labour must be getting a little bit nervous. The Greens on 10% is extraordinary…

    labour must be asking themselves how they (almost) blew it.

  20. Tops and Bottoms.

    I’ve mentioned this theory before and think it is increasingly relevant to May 2015.

    Both Lab and LD have high tops and low bottoms, within their respective VIs.

    Lab perhaps 25 to 45, LD maybe 6 to as much as 30.

    Cons, on the other hand, seem to go from around 28 to 36 but, more typically than the other two, usually seem settled at 32.

    My thinking for a long time is that the remaining near 70% are simply looking for WHICH different party to vote for. They tried LD but didn’t like the Tory connection so looked elsewhere. So they went for UKIP and now Green in response to polls.

    [Note that the LDs went off a cliff because of their Tory connection but the Tories – due to their high bottom – were relatively unscathed]

    It seems unlikely, to me anyway, that as the GE campaign gets going, a large number will think “Actually I DO like the Tories after all.” There may be some returning from UKIP but I would think 35% is the most they can hope for.

    Therefore I believe that the result will depend upon how many of those toying with SNP, UKIP, Green – who are in the main anti-Tory for varying reasons – are convinced that:

    [1] Voting that way will possibly allow a return of this coalition government and [2] they are enthused [or at least not put off] by the Labour campaign.

    The closer to May we get with the Tories still looking unlikely to be part of the next government the more likely it is that UKIP leaners will vote that way.

    All in all I think that this is the most psychologically interesting election – in terms of how the electorate respond to what each other is saying in polls – I have ever known.

    It’s a bit like footy with goals changing everything – but in politics at the moment it’s the polls that have that ability.

  21. I rest my case.

  22. @ PHIL HAINES about 09.30 on previous thread…

    http://www.statgeek.co.uk/wp-content/uploads/2014/12/ld-green-uk.png

    Over the last year, LD falls and Green gains have been quite closely matched (although Green gains have been greater).

    @CATMANJEFF soon after…
    virtually always a plot of VI for every poll of a party looks like the teeth of a saw – but somewhere in there, there are trends among the fluctuation, so while I agree it is unlikely that YouGov will show Greens as high in the next poll, it is clear that the trend is upwards – even a poll with the Greens back where they were a year ago couldn’t negate the fact that there has been a consistent upward trend beneath the ‘noise.’

  23. Sturgeon has told the BBC the SNP would vote against any Health Bills at Westminster that they see would have a negative affect on the Scottish system.

    Labour about to get crunched, especially if their leader remains in Westminster voting on issues the SNP attack as having a negative effect on the Scottish system.

    Not a fan of voting on English matters myself but we are in a union and the lack of proper federalisation in the UK is hardly an SNP fault.

  24. ROSIEANDDAISIE

    If you look at yesterdays forecast from electionforecast.co.uk you will find that their projections ranges are:-

    Con 29.4% – 37.4%
    Lab 27.7% – 35.7%

    My own view is that the Tories will end up at about 37% and Labour 30%. Labours voter share seems to be continuing to fall, the economic news continues be be encouraging (see today’s employment and wage growth figures), Labour is well behind on the economy as far as voters views go. I continue to think that the economy will be decisive.

  25. @ Hal

    ‘Apart from competition law, one of the practical things about renationalising the railways is that they would require a lot of capital to run.’

    I’m not sure that this is such a consideration. The evidence reported by ‘Action for Rail’ as that the East Coast mainline when taken back into public ownership:

    ‘Not only that but DOR on East Coast receives the lowest subsidy of any operator and returns more money back to the state than any other train operator. In 2013/14 it paid £217m to the Treasury, and since 2009 East Coast has returned over £1bn to the the taxpayer, all of which will be re-invested in the service, instead of going into the pockets of company shareholders.’

    In addition to which, there is no actual need for the Government to ‘borrow’ from the private sector to invest in rail. Even Mark Carney, gov. of BoE has proposed ‘QE’ into the real economy.

    I do not need to tell you that the polling evidence is overwhelming public support for renationalisation of the railways – approx. 80% including a majority of conservative voters.

  26. The Train Operating Companies are lightly capitalised.

    The problem is buying back the trains from the leasing companies (which attract leasing fees even when fully depreciated).

  27. @ Colin

    I am aware that there is a ‘pause’ in the TTIP negotiations with regard to ISDS. However, this reminds me of the ‘wrong’ referendum result in Ireland and the ‘pause’ in Lansley’s Health and Social Care bill… neither of which altered the final outcomes.

    In any event, ISDS is still included in CETA and the EU-Singapore trade deals which are in their finals stages of ratification. There are also secret negotiations, currently in Geneva, for TISA. Hence, even if TTIP fails to contain ISDS, subsidiaries of US companies located in Canada, Singapore, and for e.g. the Ukraine, could equally well sue (via the tribunal system comprising three private international lawyers) any UK government seeking to take rail back into public ownership.

    In fact, it may be that TTIP is the Trojan horse which is intended to distract public attention from the other bilateral trade deals, and specifically away from the potentially more wide-ranging and impactful TISA.

  28. toh

    I am analysing based on the last twenty years: Labour VI is more extreme.

    By the way, re my previous post – I am not suggesting that none of those who are saying they will vote Green or UKIP are not fully committed, just that it seems likely that not all of them are.

    Leaving enough left to make a final decision that could swing the election.

    On a personal level, which I realise is irrelevant, the more I see of EM in the HOC the less impressed I am and the more I think he needs some serious advice. If I was un-committed it wouldn’t be tempting me.

  29. THE OTHER HOWARD

    “My own view is that the Tories will end up at about 37% and Labour 30%. Labours voter share seems to be continuing to fall, the economic news continues be be encouraging (see today’s employment and wage growth figures), Labour is well behind on the economy as far as voters views go. I continue to think that the economy will be decisive”
    _____

    I agree with your analysis regarding the economy etc and helping the Tory vote but 37%? I know you’re still holding out for a Tory majority but I realistically (can’t put an exact figure on it) believe the Tories will be the largest party after the election and probably poll around the mid 30% bracket at best.

    I can’t really see them polling over their 2010 mark and none of the polls so far have shown them above that mark.

    I think what be both can probably agree on though is that DC will be PM after the election.

  30. @TOH

    So you think the Tories could well end up with their largest vote share in a general election for very nearly a quarter of a century, despite the emergence of a multiplicity of smaller parties that didn’t really feature in elections over that period, and despite them hardly ever getting anywhere near 37% in any of the polls conducted during this Parliament. Coupled with that, you think that the party (Labour) that has led in the polls pretty consistently for three years is going to go down to its third worst ever electoral performance. All this is going to happen, moreover, in just a few months time, turning over virtually every current poll configuration. Even allowing for a five year low Labour VI rating in yesterday’s YouGov, there is still not the slightest sign of any Tory recovery. Yes, Labour were on 30% according to YouGov yesterday, but so were the Tories according to ICM yesterday, and TNS had them on 28% only a couple of days before that.

    I think what you predict may well be a triumph of wishful thinking over evidence and constant repetition of an assertion doesn’t make it true.

  31. @Ben

    It’s not that close a match. If your point is that the Greens are stuffing the LDs then I agree, but they’re clearly also stuffing Labour, as Spearmint’s last set of detailed graphs showed well enough.

    The Conservatives are the clear winners. If those trends apply in marginal as well as non-marginal seats the Conservatives could easily end up with as many seats as now by capturing enough seats off the LDs to compensate for a much reduced number lost to Labour. A double whammy.

    I think Cameron’s strategy of getting the Greens into the news is paying off so far. Pressman also made a lot of that last time he was here.

  32. @ Norbold

    These trade deals signed by the EU Commision, secretly and largely without oversight under the Lisbon Treaty, are certainly good reasons to want to leave the EU IMO :)

    Ukip originally supported the trade deals but not the EU. Perhaps, realising the contradiction, they then u-turned on TTIP. But given Mr Farages u-u-turn on the NHS, we may see another on TTIP.

  33. Ipsos Mori / STV poll:

    SNP 52%
    Lab 24%
    Con 12%
    Lib 4%
    Green 4%

    Seats:

    SNP 56
    Lab 2
    Lib 1

    Not seen the tabs yet, so don’t blame me if it’s a pathetic sample.

  34. Actually the data is more specific:

    SNP 52.5%
    Lab 24.2%
    Con 12.1%

    Seats:

    SNP 57
    Lab 1
    Lib 1

    (Although the STV article says SNP 55, Lab 4 – Orkney & Shetlands is SNP gain)

  35. The main capital requirement for the railways is the infrastructure, largely owned by Network Rail, which was nationalised (very quietly) in 2014.

    While some newly ordered trains are financed by government through PFIs etc, most are leased from private owners.

    I think that the unions’ campaign for nationalisation focusses on the train operating companies, which, as Lurker says, have small capital requirements.

  36. STATGEEK

    It’s a full STV poll, 1001 polled between 12 – 19 Jan

    http://www.snp.org/media-centre/news/2015/jan/snp-welcome-lead-westminster-voting-intentions

  37. Statgeek

    Thanks for the info.

    A rather bizarre tweet from Mike Smithson caught my eye –

    “Would, I wonder, phone polls of Scotland produce different results if non-Scottish interviewers used.”

  38. PHIL HAINES

    “I think Cameron’s strategy of getting the Greens into the news is paying off so far. Pressman also made a lot of that last time he was here”
    ____

    Yes credit to PRESSMAN but he hasn’t manged to get the Greens onto the debating podium with the other leaders where they could do some real damage.

    Mind you Cleggmania and busted flush still resonates in my head.
    …………

    Slightly off topic. According to the Electoral Calculus… Renfrewshire East Glasgow area NAT gain from LAB : Jim Murphy.

    I’m thinking maybe he should avoid Dundee and stick closer to home. ;-)

  39. CROSSBAT11

    I really do not understand why you accuse me of wishful thinking, I am not a Tory, I am a economic Libertarian and therefore will have to use my vote to support the party which will do the least harm to the economy.

    ALLAN CHRISTIE

    On the actual figures of course I may well be wrong, it could equally be Cons 34% Labour 27% or Cons 32% Lab 25%. What I do expect is Cons to be 7% higher than Labour at the election.

  40. THE OTHER HOWARD

    ALLAN CHRISTIE
    “On the actual figures of course I may well be wrong, it could equally be Cons 34% Labour 27% or Cons 32% Lab 25%. What I do expect is Cons to be 7% higher than Labour at the election”
    ______

    I think this could be more plausible if i’m being honest but your figures are still hinting at a sneaky wee Tory majority aren’t they? Coochy Coochy Coochy ;-)

  41. SUE

    Is there any significant representation in the EP for views like yours which oppose these trade liberalising proposals.

    If not, I am surprised, because a number of EZ countries-noteably Greece, France & Italy still feature the most bizarre professional & trade cartels , closed shops & protectionist policies. For some, as you know, these arrangements ,along with rigid & restrictive labour laws , are at the heart of EZ economic stagnation & lack of competitiveness.

    I can only presume that , since they appear not to be reflected in significant opposition to pursuance of single market liberalisation at Commission / EP level, they represent purely domestic & historic political issues, rather than any pan-european opposition to trade liberalisation.

  42. ALLAN CHRISTIE

    Indeed I am, I still expect a small Tory majority.

  43. I think the challenge for Labour in Scotland is to come up with a convincing answer to;

    “What will a Labour MP do that an SNP one won’t”

    Under Murphy we seem to be seeing triangulation on to popular SNP policies but the underlying theme is still “Vote for Us because we’re not Them”

    It worked for Blair against Major because at the time the Tories were in a mess and blamed for the problems in the Country so time for change went down well.

    So far the few non SNP leaflets I have seen here all have Westminster Candidates attacking the SNP Government in Holyrood seeming suggesting that their priority when they get to London is to complain about Edinburgh.

    I am not sure that will work as Holyrood is hardly going to listen and the public in Scotland seem happier with Holyrood than Westminster.

    It’s all a bit odd really.

    Peter.

  44. Ipsos-MORI poll

    Net satisfaction ratings

    Sturgeon +49
    Harvie +21
    Swinney +16
    Murphy -4 (but see below)
    Davidson -8
    Rennie -17

    Cameron -40
    Miliband -45
    Clegg -50

    With Murphy new LiS leader more/less likely to vote Lab –
    More 20 : Less -28

  45. R&D
    “On a personal level, which I realise is irrelevant, the more I see of EM in the HOC the less impressed I am and the more I think he needs some serious advice.”

    The weekly session when MPs meet in the House of Commons is a bear pit & is justified apparently as an excuse for MPs to let off some steam.

    What sort of advice are you thinking of ?

    @AW
    I used the 3-letter acronym for those weekly sessions & triggered auto-mod. Please will you delete it, thanks.

  46. MORI main article with link to charts (but not yet tables) etc is here:

    https://www.ipsos-mori.com/researchpublications/researcharchive/3514/SNP-remains-in-dominant-position-as-election-approaches.aspx

    SNP 52% (-)

    Lab 24% (+1)

    Con 12% (+2)

    Lib Dem 4% (-2)

    Green 4% (-2)

    Others 3% (-)

    Changes are compared to previous MORI (22-29 Oct) and all figures are ‘certain to vote’ though as happens it only makes a difference of a point or so if you look at all voters.

    Meanwhile Nicola’s honeymoon continues while Jim is still left at the altar (possibly to be sacrificed).

    Around a third of voters (34%) are satisfied with the performance of Labour’s new leader Jim Murphy while 38% are dissatisfied and 28% are unsure so far. Around half (48%) of voters tell us that Mr Murphy’s appointment makes no difference to their likelihood of voting Labour in May, while 20% say it makes it more likely and 28% less likely.

    Mr Murphy’s ratings compare unfavourably to those for new First Minister Nicola Sturgeon, with 69% of voters satisfied compared to just 20% dissatisfied.

  47. Bramley

    Stop sounding angry: stop jabbing his finger: stop talking over a barrage of noise and, by refusing to do so highlighting it’s rudeness] make better points…

    Lots more but this ain’t the place

  48. I think it will be Con 37% Lab 32%,however as labour tend to do better in the marginals i think they will be the larger party.

  49. If the STV poll was borne out in an election, would that raise an argument for independence on the basis that more than 50% had voted for MP’s whose primary policy aim is independence?
    Such a scenario could surely have bizzare consequences Imagine a c&s deal between Tories and SNP simply on the basis that there would be an independence bill. One way to ensure that DC remains PM, perhaps for a very long time.
    Whilst unlikely it is not far fetched and shows the uncertain times we are living through.
    The Chinese have a curse “may you live in interesting times”

  50. WB

    “If the STV poll was borne out in an election, would that raise an argument for independence on the basis that more than 50% had voted for MP’s whose primary policy aim is independence?”

    Doubtless some would argue that – but it’s not the position taken by either SNP or SGP.

1 2 3 5