Posts Tagged

Forecasting

The US election result came as an absolute shock to many, but it was the pollsters that took the biggest hit. The major poll-based forecasts, a lot of models, the prediction markets, even the superforecaster crowd all got it wrong. They estimated high probabilities for a Clinton victory, even though some were more careful than others in claiming that the race would be very tight. Our prediction survey, however, was spot on thanks to the method we used for Oraclum Intelligence Systems, a start-up developed out of our academic work. We predicted a Trump victory, and we called all the major swing states in his favour: Pennsylvania (which no single pollster gave to him), Florida, North Carolina, and Ohio. We gave Virginia, Nevada, Colorado, and …

It is not hard to see why Leave won. Evidence from numerous opinion polls showed that there was a clear majority for Leave on the basis of concerns about immigration and beliefs that leaving would reduce immigration. Moreover the same opinion polls showed us that there was no compensating majority who believed that the UK would be worse off if we left. Still less did people feel that they personally would be financially worse off. For further details see here. Although it should not have come as a surprise that Leave won, the result was close enough that it could easily have gone the other way. There will be much debate as to whether the Remain side could have made their …
British Prime Minister David Cameron at the European Council meeting of 6th March 2014. Photo credit: The Prime Minister's Office.

The UK referendum on EU membership may be many months away but with David Cameron laying out his stall with other European leaders, we should be clear that we are embarked on the journey and already some way down the track. It is easy to think of referendums as one-shot deals but in reality they are not. Rather, referendums are long-term games and in this case the game was started in 2013. And it’s easy to think of this as a European process, but whatever grand meals may be consumed in other European capitals, this is very much a result of domestic British politics. The EU referendum is largely down to domestic drivers and the result will likely be shaped as much by the party politics between and within UK parties as by European factors.

With the failure of traditional forecasting methods to accurately predict the outcomes of the UK General Election of May 2015, can social media based predictions do any better? In this article, Andrea Ceron, Luigi Curini, and Stafano M. Iacus (University of Milan and VOICES from the Blogs) find that supervised and aggregated sentiment analysis (SASA) applied in proportional electoral systems produces the most accurate forecasts of election results.

Forecasters, academic experts, journalists, pollsters and the betting markets have long been forecasting a seriously hung parliament with both major parties not only short of the 326 seats required for an overall majority but even forecast to get less than 300 seats. Meanwhile, an SNP landslide is expected in Scotland which would be hugely damaging for Labour and have major implications for the government formation process. If the forecasters and betting markets are right in their central forecasts then Con+LD+DUP combined will be short of a majority and so a Labour led government should form if they can secure the support of the SNP and probably others, including the Liberal Democrats, will be needed too: a potentially messy and unstable situation but also one where there is sufficient similarity in ideological perspective for policy agreement on plenty of issues. But there is uncertainty associated with all the forecasts and some forecasters are trying to estimate the extent of that uncertainty, which in turn can be used to calculate probabilities of particular events (hung parliament, largest party, etc.)