Ukip jump to 24% in ComRes poll – but is it accurate?

A long-running debate among pollsters about how to assess the standing of smaller parties has been reignited by an experiment by ComRes for yesterday’s Independent on Sunday and the Sunday Mirror. It showed a five per cent jump in Ukip support when respondents were “prompted” that Nigel Farage’s party was one of the choices.

Some pollsters mention Ukip in their initial question along with the Conservatives, Labour and the Lib Dems. Others offer only the three well established Westminster parties plus “another party”. Only those who choose “other” are then offered the Ukip option.

ComRes decided to split its sample in two and try out both methods. Among those who were not “prompted” with the Ukip choice, the result was Con 31, Lab 34, Lib Dem 7, Ukip 19, Greens 4, Other 5.

Subscribe to The Week

Escape your echo chamber. Get the facts behind the news, plus analysis from multiple perspectives.

SUBSCRIBE & SAVE

Sign up for The Week's Free Newsletters

From our morning news briefing to a weekly Good News Newsletter, get the best of The Week delivered directly to your inbox.

From our morning news briefing to a weekly Good News Newsletter, get the best of The Week delivered directly to your inbox.

Sign up

Among those offered Ukip as a fourth named option – as in "Would you vote Conservative, Labour, Lib Dem, Ukip or some other party?" – the result was Con 29, Lab 31, Lib Dem 7, Ukip 24, Greens 5, Other 5.

In short, given the clear option of voting for Ukip, five per cent more respondents plumped for the party, ditching the Conservatives and Labour to do so.

To the layman, it might seem fairer to ask the Ukip question, bringing them in line with the other three parties. Given the extraordinarily high profile Ukip have enjoyed over the past year, and with an MP – Douglas Carswell - now in the Commons, why should they not enjoy equal billing?

To the cynic, the fact that respondents need to be “reminded” of the existence of Nigel Farage’s anti-EU party might suggest that a Ukip “vote” in an opinion poll is pretty worthless: will they remember/be interested enough to vote on election day next May?

Whichever line you take, it’s a stunning result: 24 per cent is way up from the 16-19 per cent bracket where Ukip have hovered since their Clacton by-election triumph. (The latest polling by Lord Ashcroft has Ukip on 18 per cent, with Labour leading on 31, the Tories on 28, the Greens on eight and the Lib Dems in fifth place on seven.)

And it is only one point shy of a record 25 per cent score enjoyed by Ukip in a Survation poll earlier this month for the Mail on Sunday.

John Curtice, professor of politics at Strathclyde University, calculates that 25 per cent could give Ukip as many as 128 MPs next May – if they can target the right seats with the right candidates.

Curtice also points out that this would cause the Conservatives to lose about 100 seats, and put Labour’s Ed Miliband in office.

But here’s the catch: Survation also used the Ukip “prompt” to get its 25 per cent result (arguing that “voters need a reminder of who might be on their ballot paper”) and not everyone believes it’s an accurate method.

Peter Kellner, president of YouGov, says his company adopted the Ukip “prompt” in polling for the 2004 European elections and as a result over-estimated Ukip support by four per cent and under-estimated Conservative support by five per cent.

In 2009, YouGov went over to the current practice of only mentioning Ukip in a follow-up question for people who choose “other” the first time round.

Says Kellner: “This may on the face of it seem odd or even unfair - Ukip, the Greens and the BNP all return MEPs at European elections, why should they be classed as ‘other’ parties? In practice however it worked, and produced far more accurate results. Indeed, YouGov’s final poll, for the Daily Telegraph, produced the most accurate figures of any polling company.”

Mike Smithson of Political Betting has had a forensic look at the ComRes experiment and points out that the sample who received the Ukip “prompt” produced almost twice as many supporters who hadn’t actually voted in the 2010 general election.

History shows that non-voters in one election are much more likely to be non-voters in the next. Ukip’s challenge is to get them off their sofas. The Rochester and Strood by-election on 20 November will test whether the Faragistes have the organisation to maximise their support.