Published on the LSE Europp blog on 14 March 2019
The rejection of Theresa May’s EU withdrawal deal on 12 March has given fresh impetus to those campaigning for a second EU referendum. But what are the odds that the outcome would differ from the 2016 referendum? If British voters were to be asked to cast another vote, would the Remain side gain a majority, as most supporters of a second referendum hope?
The standard way to answer these questions would be to aggregate individual, independent voting preferences, as reported in opinion polls. Yet, the recent experiences of opinion polling during the campaigns for the 2015 UK general election and the Brexit referendum have shown that this method might not necessarily yield accurate results. An alternative way is to rely on the so called ‘wisdom of the crowd’, by asking citizens themselves what the outcome of an election would be. These citizen forecasts focus on individual perceptions about others’ voting behaviour, with those perceptions averaged to form a forecast of an election result.