There are three new EU referendum polls today, a telephone poll from ORB and parallel phone and online polls from ICM.

The ORB poll for the Telegraph has topline figures of REMAIN 51%(-4), LEAVE 46%(+4), Don’t know 3%(nc) – full tables are here. The Telegraph wrote it up as immigration producing a significant swing towards Leave. I would normally have been ready to dismiss that as reading far too much into a poll that was probably just reversion to the mean: if you look at ORB’s previous figures their poll last week may have shown a thirteen point lead… but the two before that were almost identical to today’s figures. Newspapers may want to write that up as “big swing to Remain” followed by “big swing to Leave”, but a more parsimonious interpretation is just “slightly wonky sample returns to normal”.

However, today’s other polls from ICM raise more interesting questions.

ICM once again carried out two parallel polls, one conducted online, one conducted by telephone. So far all but one of these experiments have found a big gulf between phone and online polls (typically online polls show a race that’s neck-and-neck, telephone polls show a lead averaging around 8-10 points). ICM’s online poll found the sort of close race we’ve come to expect, with topline figures of REMAIN 44%(-1), LEAVE 47%(+2), Don’t know 9%(-1). ICM’s telephone poll found wholly unexpected results of REMAIN 42%(-5), LEAVE 45%(+6), Don’t know 13%(-1). Full tables for both are here.

There is nothing unusual about how the ICM poll was carried out that might explain the unusual result, it was done the same way as their previous telephone polls that showed Remain leads of seven or eight points. This leaves us with two obvious possibilities:

Either there has been a genuine movement towards Leave in recent days and the movement in the ICM poll reflects that (suggesting also that the ORB poll is showing more than just reversion to the mean), or…

ICM just got a really wacky sample by polling over the bank holiday weekend, and future telephone polls will revert to the normal pattern of solid remain leads.

Right now we can’t really tell. I will only urge my normal caveats about not reading too much into an individual poll, especially one conducted over a bank holiday weekend (whether or not that makes an actual difference or is “pollster folklore” is unclear. It’s certainly possible to point to clear examples of weird results from polls with bank holiday fieldwork, but it’s possible to point to weird results from polls conducted at other times and bank holiday results that are perfectly normal. While I’d always try to avoid polling over Easter or Christmas, I suspect in reality the Spring bank holiday doesn’t make that much difference to fieldwork). It will be interesting to see if forthcoming polls show a wider trend towards Leave, and if forthcoming telephone polls give any further suggestion that the online-phone gap may be disappearing.

156 Responses to “ICM phone poll shows Leave ahead”

1 2 3 4
  1. David
    Anthony has explained many times why all polls need to be weighted and any poll which isn’t, is just a voodoo one. Regardless of the sample size, Particularly ones like this where a website just asks you to push a yes or a no button. What controls are there to stop someone voting multiple times? And even if you do have to enter an email address, I, for example could vote 5 times (I haven’t even voted once) as I have 5 different email addresses for different parts of my life.

    I for one would be delighted if the MSE one was an accurate reflection of reality but I don’t believe it.

    Remain will win but if leave did, I will do what Paddy Ashdown did after the GE result. It would have to be a chocolate one though!

  2. That’s true, but on the other hand according to the Remain camp, the value of the £, wage levels, house prices etc. will all fall following a Leave vote, and they say prices will go up as well.

    So, at least in the short term, the economic arguments look better if we stay in. I would suggest those indicating a majority preference for Leave are looking at it from more than just a straightforward ‘will I be better off’ perspective.

  3. @Robert Newark

    The website only allows one vote per IP address, so in order to vote more than once you’d have to do so from different computers in different locations, home and work for example.

    But the same applies whether you’re voting Remain or Leave.

    As for Anthony’s theories about weighting, we all saw at the 2015 GE how inaccurate that was. If your polling is fundamentally flawed because you’re basically asking questions of a small sample of the ‘wrong’ people, that error will be magnified when extrapolated as a national percentage.

    My wife is a cake maker, and is ready to take your order for a chocolate hat.

  4. David
    All the financial projections by both sides are a load of tosh. I have lived in France during a period when the exchange rate has fallen from 1.60 down to 1.04 back up to 1.42 and now somewhere in the mid 1.20’s. When it’s high it benefits uk pensioners in Spain and France, when it’s low, it benefits uk exporters.

    High house prices benefit my generation, a fall would benefit the next generation, who can’t afford one at the moment.

    The fact is, both those scenarios have happened already, whilst in the eu. So what’s to fear from them on an exit?

    For me it’s all about keeping a lid on our population growth but yes I do believe the uk will flourish economically, when freed from the EU yoke, as well. Oh and I don’t want ttip either, where the unelected commission are undertaking talks in total secrecy. That’s about as undemocratic as you can get.

  5. Robert Newark
    There are several methods which can be used to prevent multiple voting including ip monitoring and cookies. Of course people can get around that if they really want, but there’s perhaps less incentive than for a Newspaper website where the results of voting are very public.

  6. In gratitude to JamesE I have calculated the rank correlations between the date of polls and the proportion for remain as from 4th September 2015 and 31st May this year. I have calculated separate correlations for phone polls, online polls and ICM online polls. I have also looked at the proportion of Don’t knows and won’t votes. The answers should be viewed with scepticism and checked by anyone really interested in them as my ability to enter wrong numbers into a spreadsheet is very great,

    The earliest date is ranked 82 and the most recent 1. So a positive correlation with a date means that there was a higher proportion earlier than there is now. For what it is worth the figure are:

    Phone remain .29 (p=.18)
    Phone D/K .37 (.064)
    Online Remain .07 (p=.63)
    Online DK .30 (p=.02)
    ICM online remain .34 (p=.1)
    ICM online D/K ,83 (.001)

    Within types of approach (phone or online) there is not a significant difference between companies on the online polls but there is among the phone polls. Here ipsos/mori is by far the most optimistic from remains point of view and ICM by far the least. It would be interesting to know what it is about the way they put their questions or get their samples that accounts for this difference.

    It is possible that the lack of a very strong correlation between date and percentage remain reflects contrasting trends e.g. because remain began by winning the argument on the economy and Brexit is now winning it on immigration. However, a scatter dot graph doesn’t reveal any strong evidence for this on either method of polling.

    The strongest correlation is the change in the proportion of Don’t know/ wont vote in the ICM on line polls. People there seem to have become increasing definite about what they will do. Presumably this is something to do with ICM’s methodology or the way I have copied the figures as the remainder of the online companies do not show this trend. Within the telephone polls, however, there is a trend for a decreasing proportion of don’t knows which is what one would expect if people are making up their minds. If anything this trend seems to favour Brexit but this is not a statistically significant association,

    So overall as far as these figures go there doesn’t seem to have been much of a change in terms of how people are voting since last September, The time to place bets on leave should be immediately after an IPSOs MORI poll while a remain bet should follow an ICM phone poll or failing that any online poll.

    None of this predicts the future and it may be that leave has reached a tipping point and is about to break out and race for the finish. Meanwhile I get a text from my foster son (well not really but he was homeless when he came to us and had been in care). He and his partner are probably voting out on the grounds that we don’t make our own laws, we will be freer to trade with other countries and will be stronger. I think that’s bonkers but at least my wife and I don’t seem to have stopped him from having his own opinions. Problem is that a lot of other people seem to have stepped into the gap we left.

    phone polls –

1 2 3 4