Remain leads on a knife edge: The latest EU poll dissected

Scaremongering works, apparently. That’s according to a new poll of hard-to-reach voters on the upcoming EU referendum.

Of the 1,632 voters polled by NatCen Social Research, 53 per cent backed Remain, compared to 47 per cent for Leave.

And yet the poll has a second message – the margin of error is such that the possibility of a swing to Leave cannot be ruled out.

Since the surprise Tory general election last year, polls have seemed less trusty guides than before. So why should we believe this one? And how can it say two things at once?

The answer comes down to methodology, and in this case that rests on the timing and the voters interviewed.

Reluctant voters spoke

Pollsters blamed their misplaced predictions of 2015 on self-selected respondents, who were more politically aware than the average voter.

For this poll, though, NatCen Social Research pursued the reluctant respondents for answers. Rather than looking for volunteers, researchers selected voters at random and followed up their initial message with phone calls.

The survey also takes into account the likelihood that voters will actually haul themselves down to the polling booth and make their mark on the day.

Margin for error

For Remain voters who have been nodding happily along, this is where the music stops. The researchers say a vote of 50 per cent lies within the survey’s statistical margin of error: “Even leaving aside the possibility of a late swing, the possibility of a majority for Leave cannot be ruled out.”

While those polled on the phone tended to opt for Remain, those surveyed on the internet were split exactly down the middle.

Prof John Curtice, NatCen Senior Research Fellow, said: “Our survey provides valuable insight into how to interpret the divergent results that have been produced by internet and phone polls throughout the referendum campaign. It strongly suggests that the truth may well lie in between the two.

“This implies that, in the final days before the vote, it may well be reasonable to split the difference between the online and phone polls.

“However, it is important to remember that the outcome looks so close that any lead should be treated with caution.”