Thinktank More in Common recently published an MRP (multi-level regression with post-stratification) poll which appears to show that if there was a general election in the near future, Reform would win 180 seats. According to the analysis, Labour and the Conservatives would win 165 seats each and the Liberal Democrats 67. The modelling suggests that Labour could lose 246 seats including 153 to Reform and 64 to the Conservatives.
More in Common claims that this is not a prediction of the result of the next election, writing: “With four and a half years before the next general election must be called this model is unlikely to represent anything close to the ultimate result and should not be seen as a projection of the election.” Despite this health warning, the poll has spooked some political journalists.
It is worth remembering how MRP surveys work. Agencies ask a very large sample of electors about their voting intentions – enough to have an average sample size of about 25 respondents in each of the 632 constituencies in Great Britain. This allows them to use data from the census and other sources to identify constituency characteristics which influence individual voting decisions, such as social class, age and income.
