Let’s dive in with a look at the three models, all based on polls.
Source:FT Brexit Poll Tracker
Economist Brexit Tracker
April 21 appears to be an outlier, with a sudden surge in undecideds, all breaking towards remain, followed by a reversal to previous trends.
Unlike the other sites, the Economist allows breakouts by age. I think age may determine the outcome, so let’s look further.
Economist Brexit Tracker Young
Economist Brexit Tracker Old
Bloomberg Brexit Tracker
Source: Bloomberg Brexit Tracker
I cannot read the numbers. The chart above reads “It’s too close to call, with still-undecided voters likely to determine the outcome.”
A second chart shows Brexit Odds only 22%.
The data isn’t Bloomberg’s compilation, but rather analysis by Matt Singh of NumberCruncherPolitics.UK.
Number Cruncher Politics
On May 11, Matt Singh gave an EU Referendum Update stating “It’s Not Neck-and-Neck“.
Last week’s midterm elections managed to take the focus away from the EU referendum, but only temporarily. There hasn’t been a great deal of referendum polling over that period, so the NCP model remains little changed, showing a 77.7% chance of Britain voting to Remain.
In today’s Times, Danny Finkelstein discusses online versus phone polling, with reference to the NCP/Populus joint work, plus anecdotes about the SDP and washing powder. Since James Kanagasooriam and I did the analysis, a few things have happened. The gap between the modes has narrowed further. We’ve also had the devolved elections in which, as I noted yesterday, 10 of the 12 online polls in the final two weeks overestimated support for UKIP, and none underestimated it.
If you say that the race is neck-and-neck, you implicitly assume that online is right and phone is wrong. There’s nothing wrong with taking that view, but it’s not one that most people realise they’re taking.
The problem for those of us trying to do objective analysis is that phone polls haven’t been coming around all that often, and the ones we do get, tend to be at roughly the same time of the month.
Matt Singh Brexit Probability
I too distrust online polls believing them to be less accurate. The problem I have with Singh’s 22.3% Brexit odds is there have not been enough recent telephone polls.
Both the Economist’s and Financial Times’ Brext tracker show undecideds breaking more towards Brexit than Stay as the percentage of undecideds declines.
It is this trend that is important, in my opinion.
And since the Financial Times breaks out online and telephone polls separately, let’s take a stab at plotting the trend in telephone polls.
I don’t have the data so I am just eyeballing trends here.
Look at the undecideds. For some reason the number of online undecided voters is way higher than the number of phone undecideds, especially since March 1.
Yet, as the overall trend towards a lower number of undecideds picks up, so does support for Brexit.
I would expect these polls to be of “likely” voters. But “likely” and “certain” are two different things.
Are UKIP voters more likely to turn out to vote than other classes? One would expect so, and by an overwhelming margin.
In reference to May 2016 elections, Singh note that in “10 of the 12 online polls in the final two weeks overestimated support for UKIP, and none underestimated it.”
Were the polls wrong or was the “likelihood of voting wrong“. If you think your vote does not matter, you are less inclined to vote.
Attitudes come into play. So does age.
I sense Singh is falling into Nate Silver’s trap of over-reliance on methodology that is simply wrong.
- “Stay” is still ahead in telephone polls, but there have not been enough recent telephone polls.
- There is a huge discrepancy in the number of online undecided voters and telephone undecided voters.
- Trends suggest undecideds are breaking towards Brexit.
- Will the young turn out to vote?
- Are the old more likely to vote than the young?
- On average are “Brexit” supporters more passionate (and thus more likely to vote) than “Stay” supporters.
In the May election, online polls showed a bias towards UKIP.
However, it may be a big mistake to presume the same bias is in Brexit polls.
UKIP votes are more likely to vote now than in the May general election in which UKIP candidates may not have much of a chance.
Four Things Will Decide the Election
- Trends in undecided voters. Will the current break towards Brexit pick up, or stall?
- Will more older voters than younger voters show up?
- Do the online polls overstate UKIP? Is this the same as the May 2016 general election?
- Any number of things the EU says or does between now and June 23 could tip this thing. EU surprises are more likely to benefit “Brexit” rather than “Stay”.
“Stay” is not a 77.7% chance. Given current trends and various unknowns, it’s far too early to have that much confidence.
Mike “Mish” Shedlock