Brexit and unmerited complacency

Friday morning was a strange one for me. As I tried to come to terms with the fact that the country has made what I believe to be a catastrophically short sighted decision, at the same time I was receiving emails and Tweets congratulating me on the fact that Opinium were one of only two polling companies (congratulations TNS) to predict a 'Leave' vote.

Read more »

Some thoughts on the EU referendum polling

Discounting yet another Daily Express voodoo poll, the story since David Cameron’s renegotiation deal was announced has been that a YouGov poll showed a sharp move towards leaving the EU after showing a near tie a few weeks ago.

But actually we won’t be able to tell if there has been a move until we see what the phone polls are saying and can put together a more holistic picture.

The issue with the EU referendum polls for the last few months has been that telephone polls (ComRes and Ipsos MORI) have shown a strong 15-20 point lead for “Remain” while online polls (YouGov and ICM) have shown a much tighter race, often a dead heat. We haven’t published any polls on this but what work we have done (internally and for clients) has been fairly consistent with other online polls.

So which mode should we trust for the referendum?

It’s a bit strange because the results at last year’s general election found that telephone polls and online polls performed as well or badly as each other. Historically telephone polls performed better in general elections (2010 and 2005 being examples) but last year’s election result shows that this advantage has dissipated as the response rate to telephone polls has continued to diminish.

With that in mind, here are two things that have informed how I view the referendum polls:

1. The main reason for the polling failure was that both telephone and online samples spoke to, among others, too many overenthusiastic young, liberal Labour leaning voters who all claimed to be 10/10 certain to vote. These were then treated as being representative of an age group which in reality has the lowest turnout of all.
   The people we surveyed probably did go out and vote exactly as they said they would but we didn’t talk to enough people who were more representative of these groups (politically unengaged and unlikely to vote) and as a result had too many Labour voters in our samples.
   
2. The last major modal difference in polling was after April 2012 when UKIP started to consistently poll higher than the Lib Dems. This was mainly shown in online surveys with telephone polls showing UKIP rising but nowhere near as high as the online polls were showing. Because this was such a new and unexpected phenomenon, polling models didn’t know how to properly correct for it so there was an ongoing debate over how well UKIP were actually doing.

In 2012, 2013 and early 2014 the view at Opinium was effectively “this is what the numbers are showing without any extra adjustments, let’s see how they do in an actual election before we make any judgements”. Then in the 2014 European Parliament elections, we overstated UKIP by about 5 points along with TNS, ComRes and Survation (post mortem here). We took this result into account for our general election methodology and ended up predicting UKIP’s share of the vote pretty accurately.

However, the lesson I took from this was that the raw results from online panels were a bit too “Ukippy” vs. the actual population and that this is related to the polling failure in the 2015 general election. We had two unrepresentative groups who were having too big an impact on the final VI numbers but only corrected for one of them before the election.

I suspect something similar may be happening with the referendum polls. The group that is most pro-UKIP are those aged 65+. The age group that is the most difficult to reach online is aged 65+ and therefore we may be over-representing the views of the most politically engaged of the 65+ age group. The difference between the telephone and online results also seems to be coming from this 65+ age group. Where online surveys show them overwhelmingly in favour of leaving the EU, telephone polls show a much closer margin.

It is possible that the same thing as happened in the election with young people is happening again with online polls over-representing the easiest over-65s to reach on panels who happen to be more pro-Brexit than the rest of their age group. The difficulty here is that this is happening after all of our corrections for UKIP have been taken into account and is an issue which, in theory, shouldn’t exist.

The other thing that’s possible is that social desirability and interviewer effect are having an impact. The giveaway for social desirability is that respondents don’t want to seem uninformed and are reluctant to answer “don’t know”. “Don’t know” figures are typically about 10 points higher in online EU referendum polls than telephone so this may be a factor.

I’ve been looking for evidence that social desirability bias increases with age and haven’t found any yet (though that is more down to me than anything else) but that’s a possible explanation as well, particularly if telephone polls are reaching more unengaged over 65s and if staying in the EU is the socially desirable position (something which would be enhanced by the respective leaders of each campaign).
The other side of the social desirability argument is that if it is causing more people who don’t have an opinion to say that they would vote to stay in the EU then the leads for “remain” in phone polls are phantom.

What is the upshot of all this? 

Basically that I think the ‘true’ answer is somewhere between what the telephone and online polls are saying at the moment.

That’s a bit of a cop-out I admit but I think both methods have different flaws and hopefully looking at both of them gives us a more accurate picture until polling companies find a way to correct those flaws.

No Jeremy Corbyn does not prove that a more open ballot is a mistake

One of the more controversial pieces of underreported news of the past few months was that the Labour party are apparently not going to release a breakdown of the leadership ballot by membership type. This means that there will be no published details of how full members voted versus the £3 supporters or trade union affiliates.

This is in part to avoid a 2010 situation where is was very clear that Ed Miliband had only triumphed because of overwhelming union support after losing to his brother in both the membership and MPs sections of Labour's now defunct electoral college.

Would it challenge the legitimacy of the new leader if we discovered that they had lost the membership ballot but won because of the £3 supporters and trade union affiliates? I suspect this won't be as Jeremy Corbyn will likely storm all three sections given the massive changes in party membership since 2010 but even if it were the case that the traditional membership voted for Andy Burnham but Jeremy Corbyn was pushed over the top by union affiliates and £3 supporters it wouldn't be an argument for restricting the franchise.


Read more »

Thoughts on the London Labour hustings

On Sunday I went to the London Labour hustings to see the various leadership candidates pitch themselves. Confusingly this took place at the same time as the pre-recorded Sunday Politics debate was being broadcast so there was a bit of a let-down that Andrew Neil wouldn't be there.

I went in with a couple of assumptions about Labour and the next few years:

1. Given the boundary changes and Labour's otherwise terrible position the best case scenario for the red team in 2020 is probably largest party in a hung parliament. More realistic aspirations include depriving the Tories of a majority and creating the type of hung parliament we thought would happen this year.
2. Austerity is to the 2010s as trade union law and privatisation were to the 1980s, an issue which splits the Labour party between activists and MPs but where the Conservatives (and much of the public) are broadly united. This makes any opposition an always precarious balance between irreconcilable factions and it is no surprise that Labour didn't re-enter office until the 1990s when one side of the major divisive issue had clearly won and a new consensus been established.

So, to the various candidates


Read more »

Some thoughts on the Labour leadership contest

We're a month into the contest to replace Ed Miliband so here are my thoughts on the process rather than individual candidates so far:

1. Whoever wins should pledge to make it easy to remove them
Having been led into two general elections by people the party had very serious doubts about for many years beforehand I suspect the desire to pick a winner will be a bit stronger within the Labour party than in 2007 or 2010 when the comfort zone was an appealing retreat after years of Blairism. However, the fact remains that Labour are picking their 2020 candidate for prime minister nearly five years before that election and circumstances could change enormously between now and then. In 2020 we'll have had a European referendum and possibly another Scottish referendum if England but not Scotland votes to leave the EU. Not to  mention the fact that the state of the economy and foreign affairs will be unpredictable and the Conservatives may have just elected a new leader as well.
I appreciate that nobody wants to run as an interim candidate and the idea of scheduling another leadership contest for 2018 automatically diminishes the authority of the winner in 2015 even though it is superficially appealing. Instead the current candidates should pledge to change the rules to make it easier to challenge an incumbent leader. It may be making a rod for their own back, particularly if they are in trouble in 2018 or so with the new Tory PM enjoying a honeymoon but I suggest it would be seen as a sign of confidence to propose it and will give a boost to whoever suggests it first.


2. The leader and deputy leader contests should be held at different times
Imagine that you want a balanced ticket with a centrist leader and a left wing deputy or the other way around. Let's say that you want a more centrist deputy leader like Angela Eagle if Andy Burnham wins the leadership but a more traditional left winger like Tom Watson to balance out a Liz Kendall leadership. What are you to do?
The 2007 process was hugely flawed (more on this later) as everyone knew the contest for the top job was Gordon Brown running against himself and so everyone knew the situation that the deputy would be working in. In 2010 Harriet Harman was the incumbent and provided the context there but in 2015 both jobs are up for grabs and the winner of one might help determine your choice for who should win the other but this is not possible under the current rules.
One should come before the other and I would suggest that the deputy leadership election should come second. In the US the vice presidential candidate is chosen to complement the strengths and weaknesses of the presidential candidate and something similar would make sense for Labour.


3. The process by which Labour MPs nominate their candidates should be a secret ballot
Back to 2007 again when Gordon Brown was nominated by 313 of the 355 Labour MPs meaning that no other candidate had enough nominations to run. Why did 88% of the PLP nominate Gordon Brown? No doubt many or most thought he was clearly the best candidate but the fact that he was likely to win no doubt played a part and there was nothing to be gained by opposing him. The fact that the nominations had to be public took Brown's victory from 'odds on' to 'bookies paying out before the event' because it became a virtuous (vicious?) circle of nominations and inevitability feeding each other until no other candidate could stand.
Coming back to 2015, the early part of the contest had candidates shocked at how many nominations Andy Burnham had apparently already secured. Again, no doubt much of this is genuine belief in Burnham as a candidate but the perception of him as the likely winner is surely a big factor. Imagine that the nominations were a secret ballot or, better yet, imagine that nominations had been a secret ballot in 2007.
Alternatively, perhaps the minimum should be a maximum? Once the 15% of the PLP have nominated one candidate then no others should be allowed? Given that elected officials no longer constitute 1/3 of the Labour electoral college their individual votes aren't likely to make a huge difference so individual nominations are little more than expressions of support and signalling. If no candidate can receive more than 15% then it would help reduce the risk of other candidates not even making it onto the ballot as in 2007. Jeremy Corbyn's recent entry has helped shake things up a little by potentially giving the Labour left a candidate who is definitely 'of them' but whether he'll make the ballot is unclear despite the fact that I suspect a large proportion of members would vote for him if he did.

I'm sure there are feasibility problems with all of these suggestions and given the institutional inertia of the Labour party none are likely to come to pass but those are my thoughts after watching the first month of this and in anticipation of the three still to come.

Some general election thoughts

So the election is over and the polling industry had a bit of a nightmare. We'll get to that in a few days time as we pore over spreadsheets and come up with explanations and solutions. Our initial statement is here and we'll be putting up a more detailed breakdown later this week..

So here are some more general observations that came into my head as I powered myself through election night and the day after with eye watering quantities of coffee and red bull.


Read more »

Despite the hung parliament, who wins the election matters

Another one from "the other place" so, again, apologies about charts not quite fitting. This is about the potential legitimacy crisis that we're heading for if the party that 'loses' the election forms the government. In practice, I suspect that Conservative supporting newspapers will support any arrangement that puts the Conservatives back in office as just and proper while any arrangement that puts Labour in will be a stitch-up or a coup. Similarly for the Labour supporting papers.

Here's the actual post and I've added a few more comments at the end.

Most sensible predictions for the election are that, barring a late swing one way or the other, Britain will elect another hung parliament in May. Whether the Conservatives or Labour are the largest party varies between forecasts but, either way, on May 8th David Cameron and Ed Miliband will be scrambling around trying to put together a deal with the other parties to form a majority in the House of Commons.

In 2010 the fact that the parliamentary arithmetic so favoured a Conservative-Lib Dem deal meant that we didn’t face the issue of the party that ‘won’ the election not forming the government. That is much more of a possibility in 2015 and any government that emerges could face a crisis of legitimacy, regardless of what is constitutionally proper.

Read more »