One of Britain’s most reputable pollsters admitted that the methodology it used for EU referendum surveys was flawed and resulted in public support for a Brexit being overstated.
YouGov published its latest referendum voting intention survey on Wednesday, which showed a four-point lead for Remain (44% > 40%).
However, a more interesting detail to come out of YouGov’s most recent release were the changes the firm has made to how it collects its data.
The research group — which conducts its referendum surveys for The Times newspaper — said that its past polls have over-represented UKIP supporters, who are some of the most likely people to vote for Britain to leave the EU on June 23.
In the release, YouGov said:
We have made a slight change in our methodology since our previous poll. While our polls at the Scottish, Welsh, and London elections were generally very accurate, one consistent flaw was that we had UKIP too high.
This error appears to be related to the switch from weighting by party ID to weighting by past vote.
Comparing our sample to the British Election Study, people in our polls who voted for “establishment” parties like the Conservatives and Labour in 2015 were not likely enough to also identify with the party, people who voted for “challenger” parties like UKIP and the Greens in 2015 were too likely to identify strongly with them.
Business Insider contacted YouGov on Wednesday to find out if the firm had been using the old methodology for its EU referendum polling. Joe Twyman, Head of Political and Social Research, confirmed over the phone that they had.
The reason for the overrepresentation of UKIP supporters in was that the old polling methodology focused heavily on what parties respondents voted for in the 2015 general election as a variable.
This was an issue because people who voted for Nigel Farage’s party in last year’s election are very likely to identify as fully-fledged supporters today.
Not as many people who voted for Labour or the Conservatives, though, are as likely to identify as committed supporters of the parties. This means that supporters of the anti-EU party who have been surveyed have enjoyed a disproportionately large voice.
If YouGov hadn’t tweaked its methodology, the poll it published on Wednesday, for example, would have put the Remain camp three points ahead instead of four, The Times told Reuters.
YouGov’s latest survey is one of a number of EU referendum polls which have been released so far this week. How exactly the vote will turn out remains difficult to predict, with phone polls showing big leads for Remain, while online surveys have suggested much closer contests.
Business Insider Emails & Alerts
Site highlights each day to your inbox.