'What are the odds? Using Constituency-level betting markets to forecast seat shares in the 2010 UK general elections'

Paper presented at the Elections, Public Opinion and Parties Annual Conference at the University of Essex, UK, September 2010.

This article focuses on the usefulness of a novel source of data for forecasting party seat shares in the UK’s legislative elections. Forecasters of this property face what we call the ‘votes-to-seats’ problem, due to the operation of the Single Member Plurality (SMP) electoral system. SMP means that it is not straightforward to predict how national-level vote shares will translate into national-level seat shares. We review existing approaches to this problem and argue that a new data source – the availability of constituency-level estimates of each candidate’s likelihood of winning their seat from betting markets – could potentially provide a ‘short cut’ that would allow seat forecasters to elide the votes-to-seats problem. The article then investigates methodologies for translating data from constituency-level betting markets in each of the UK’s 650 constituencies into aggregate, national-level predictions of parties’ seat shares. The accuracy and volatility of forecasts produced from constituency-market gambling data from the site Betfair.com are evaluated at four time points during the campaign. The article concludes by examining the future usefulness of constituency-level betting markets for forecasters seeking to predict seat outcomes in SMP systems.

Full paper available to download via the EPOP 2010 conference page of the University of Essex website.

Back to 2010