We’ve had three voting intention polls in the last couple of days:

  • Ipsos MORI‘s monthly political monitor had topline figures of CON 43%(+4), LAB 42%(nc), LDEM 6%(-3). Fieldwork was over last weekend (Fri-Wed), and changes are from January. Tabs are here.
  • YouGov/Times on Friday has toplines of CON 41%(nc), LAB 43%(+1), LDEM 7%(nc). Fieldwork was Mon-Tues and changes are from last week. Tabs are here.
  • Survation/GMB, reported in the Sunday Mirror, has CON 37%(-3), LAB 44%(+1), LDEM 9%(+1). Fieldwork was Wednesday and Thursday, and changes are from the tail end of January. No tabs yet.

There is no clear trend – Labour is steady across the board, Survation have the Tories falling, MORI have them rising. MORI and YouGov show the two main parties neck-and-neck, Survation have a clear Labour lead.

The better Labour position in Survation is typical, but it’s not really clear why. As regular readers will know, Survation do both online and telephone voting intention polls. Their phone polls really do have a significantly different methodology – rather than random digit dialling, they randomly select phone numbers from consumer databases and ring those specific people. That would be an obvious possible explanation for a difference between Survation phone polls and polls from other companies. However, this poll wasn’t conducted by telephone, it was conducted online, and Survation’s online method is pretty similar to everyone else’s.

Survation’s online samples at the general election were much the same as everyone elses. The differences were down to other companies experimenting with things like demographic turnout modelling in order to solve the problems of 2015, approaches that ultimately ended up backfiring. However, polling companies that got it wrong have now dropped the innovations that didn’t work and largely gone back to simpler methods on turnout, meaning there is now no obvious reason for the difference.

Meanwhile, looking at the other questions in the surveys the YouGov poll also included their all their regular EU trackers, following Theresa May and Jeremy Corbyn’s speeches. Neither, unsusprisingly, seem to have made much difference. 29% of people think that the Conservative party’s policy on Brexit is clear, up on a week ago (25%) but still significantly down from January (37%). 36% of people say they support May’s approach to Brexit, barely changed from a week ago (35%). For Labour, just 18% of people now think their Brexit policy is clear (down from 22% straight after Corbyn’s speech), 21% of people say they support the approach that Jeremy Corbyn is taking towards Brexit.


Survation have a poll in today’s Mail on Sunday. Topline figures are CON 37%(-1), LAB 45%(+1), LDEM 6%(-1). Fieldwork was Thursday and Friday and changes are since early October.

The eight point Labour lead is the largest any poll has shown since the election, so has obviously attracted some attention. As regular readers will know, Survation carry out both telephone and online polls. Their telephone method is unique to them, so could easily explain getting different results (Ipsos MORI still use phone polling, but they phone randomly generated numbers (random digit dialling), as opposed to Survation who phone actual numbers randomly selected from telephone databases). However, this was an online poll, and online there is nothing particularly unusual about Survation’s online method that might explain the difference. Survation use an online panel like all the other online polls, weight by very similar factors like age, gender, past vote, referendum vote and education, use self-reported likelihood to vote and exclude don’t knows. There are good reasons why their results are better for Labour than those from pollsters showing the most Tory results like Kantar and ICM (Kantar still use demographics in their turnout model, ICM reallocate don’t knows) but the gap compared to results from MORI and YouGov don’t have such an easy explanation.

Looking at the nuts and bolts of the survey, there’s nothing unusual about the turnout or age distribution. The most striking thing that explains the strong Labour position of the poll is that Survation found very few people who voted Labour in 2017 saying they don’t know how they would vote now. Normally even parties who are doing well see a chunk of their vote from the last election now saying they aren’t sure what they would do, but only 3% of Labour’s 2017 vote told Survation they weren’t sure how they would vote in an election, compared to about 10% in other polls. Essentially, Survation are finding a more robust Labour vote.

Two other interesting findings worth highlighting. One is a question on a second referendum – 50% said they would support holding a referendum asking if people supported the terms of a Brexit deal, 34% said they would be opposed. This is one of those questions that get very different answers depending on how you ask it – there are plenty of other questions that find opposition, and I’m conscious this question does not make it clear whether it would be a referendum on “accept deal or stay in EU”, “accept deal or continue negotiations” or “accept deal or no deal Brexit”. Some of these would be less popular than others. Nevertheless, the direction of travel is clear – Survation asked the same question back in April when there was only a five point lead for supporting a referendum on the deal, now that has grown to sixteen points (50% support, 34% opposed).

Finally there was a question on whether Donald Trump’s visit to the UK should go ahead. 37% think it should, 50% think it should not. This echoes a YouGov poll yesterday which found 31% think it should go ahead, 55% think it should not. I mention this largely as an antidote to people being mislead by twitter polls suggesting people want the visit to go ahead – all recent polls with representative samples suggest the public are opposed to a visit.

Tabs for the Survation poll are here.


-->

Kantar have published a new voting intention poll ahead of the budget, the first I’ve seen from them since the general election. Topline figures are CON 42%, LAB 38%, LDEM 9%, UKIP 5%. Fieldwork was between last Tuesday and this Monday.

This is the first poll to show a Conservative lead since September and the largest Tory lead in any poll since the election. As ever, it’s best to look carefully at any poll that shows an unusual result before getting too excited/dismayed. The reason for the unusual result appears to be methodological, rather than from some sudden Tory recovery, and down to the way Kantar treat turnout. As regular readers will know, many polls came horribly unstuck at the 2017 election because instead of basing turnout on how likely respondents said they were to vote, they predicted respondents likelihood to vote based on factors like their age and class. These methods assumed young people would be much less likely to vote, and produced large Conservative leads that ended up being wrong. Generally speaking, these socio-economic models have been dropped.

At the election Kantar took a sort of halfway position – they based their turnout model on both respondents’ self-assessed likelihood to vote, whether they voted last time and their age, assuming that older people were more likely to vote than younger people. This actually performed far better than most other companies did; Kantar’s final poll showed a five point Conservative lead, compared to the 2.5 they actually got. As such, Kantar appear to have kept using their old turnout model that partly predicts likelihood to vote based on age. The impact of this is clear – before turnout weighting Labour would have had a one point lead, very similar to other companies’ polls. After turnout weighting the Conservatives are four points ahead (the full tabs and methodology details are here).

(Another noticable difference between Kantar’s method and other companies is that they use the leaders’ names in their voting intention question, though given there is not nearly as much of a gap between Theresa May and Jeremy Corbyn’s ratings as there used to be I’m not sure that would still have an impact.)


Yesterday the British Polling Council had an event talking about how the polls had changed since 2015. This included collecting up data from all the companies on what they’ve done to correct the error and what they are now doing differently – all those summaries are collected here.

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.

So, what have polling companies done to correct the problems? There is a summary for each individual company here.

There have been a wide variety of changes (including YouGov interlocking past vote & region, ICM changing how they reallocate don’t knows, ICM and ComRes now both doing only online polls during the campaign). However, the core changes seem to boil down to two approaches: some companies have focused on improving the sample itself, trying to include more people who aren’t interested in politics, who are less well educated and don’t usually vote. Other companies have focused on correcting the problems caused by less than representative samples, changing their turnout model so it is based more on demographics, and forcing it to more accurately reflect turnout patterns in the real world. Some companies have done a bit of both.

Changes to make samples less politically engaged…

  • ICM and YouGov have both added a weight by respondents level of interest or attention to politics, based upon the British Election Study probability survey. YouGov have also added weights by level of educational qualification.
  • Ipsos MORI haven’t added political interest weights directly, but have added education weights and newspaper readership weights, which correlate with political interest.
  • Kantar have added education weighting, and also weight down turnout to the level they project it to be as a way of reducing the overall level of political engagement in their sample.

Changes to base turnout on demographics…

  • ComRes have changed their turnout model, so it is based more on respondents’ demographics rather than how likely they claim they are to vote. The effect of this is essentially to downweight people who are younger and more working class on the assumption that the pattern of turnout that we’ve seen at past elections remains pretty steady. ICM have a method that seems very similar in its aim (I’m not sure of the technicalities) – weighting the data so that the pattern of turnout by age & social grade is the same as in 2015.
  • Kantar (TNS) have a turnout model that is partially based on respondents age (so again, assuming that younger people are less likely to vote) and partially on their self-reported likelihood.
  • ORB weight their data by education and age so that it matches not the electorate as a whole, but the profile of people who the 2015 British Election Study who actually voted (they also use the usual self-reported likelihood to vote weighting on top of this).
  • Opinium, MORI and YouGov still base their turnout models on people’s answers rather than their demographics, but they have all made changes. YouGov and MORI now weight down people who didn’t vote in the past, Opinium downweight people who say they will vote for a party but disapprove of its leader.
  • Panelbase and Survation haven’t currently made any radical changes since 2015, but Panelbase say they are considering using BES data to estimate likelihood to vote in their final poll (which sounds to me as if they are considering something along the lines of what ICM are doing with their turnout model)

In terms of actual outcomes, the pollsters who have adopted demographic turnout-models (ComRes, ICM and Kantar) tend to show larger Conservative leads than companies who have tried to address the problem only through sampling and weighting changes. We cannot really tell which is more likely to be right until June 8th. In short, for companies who have concentrated only on making samples more representative, the risk is that it hasn’t worked well enough, and that there are still too many of the sort of young engaged voters who are attracted to Jeremy Corbyn in their samples. For companies who have instead concentrated on demographic-based turnout models, the risk is that the pattern of turnout in 2017 differs from that in 2015, and that Jeremy Corbyn’s Labour really does manage to get more young people to come out to vote than Ed Miliband did. We will see what happens and, I expect, the industry will learn from whatever is seen to work this time round.


Two new voting intention polls today. The first by Survation for Good Morning Britain had topline figures of CON 48%(+1), LAB 30%(nc), LDEM 8%(+1), UKIP 4%(nc). Clearly there is no substantial change since their poll a week ago. Fieldwork was conducted on Friday and Saturday, after the leak of the Labour manifesto, and doesn’t show any sign of any impact.

The second was the weekly ICM poll for the Guardian. Topline figures there are CON 48%(-1), LAB 28%(+1), LDEM 10%(+1), UKIP 6%(nc). As many have noted, ICM are now are, along with TNS, one of only two pollsters still showing Labour support below thirty points (MORI last poll did the same, but that was several weeks ago when everyone showed Labour that low). It’s not that ICM haven’t shown Labour support rising a little. ICM have been showing Labour recovering slightly, it’s just they’ve been doing so at a slightly lower figures: at the start of the campaign ICM had Labour at 25-26% and they now have them at 27%-28%.

This seems to be a consistent methodological difference. The methodological differences between pollsters are complicated and various, and some of them work in opposite directions (ICM, for example, also reallocate don’t knows in a way that helps Labour) but the most obvious one at the moment is probably the approach to turnout. Traditionally British pollsters have accounted for people’s likelihood to vote by getting respondents to estimate their own likelihood to vote – put crudely, they ask people to say how likely they are to vote on a scale of 0 to 10, and then either weight them accordingly (someone who says they are 8/10 likely to vote is only counted as 8/10ths of someone who says 10/10), or apply a cut off, ignoring people who rate their chances below 5/10 or 9/10 or 10/10. Since 2015 several companies, including YouGov and Ipsos MORI, have also factored in whether people say they have voted in the past, weighting down past non-voters.

ICM and ComRes have adopted new approaches. Rather than basing their turnout model on people’s self-reported likelihood to vote, they base it on their demographics – estimating respondent’s likelihood to vote based on their age and social grade – the assumption being that younger people and working class people will remain less likely than older, more middle class people to vote. This tends to have the effect of making the results substantially more Conservative, less Labour, meaning that ICM and ComRes tend to produce some of the biggest Tory leads.

Full tabs for the ICM poll are here and the Survation poll here.