Fifth combined forecast for the 2024 general election

By Stephen Fisher, John Kenny, Paul Furey, and Polina Ryzhuk. 26th June 2024.

The average of different kinds of seats forecasts points to a Labour majority of 200; the same as last week. There is very little change for other parties, except that the average forecast for the Conservatives is down from 127 last week to 123 this week. That is despite a rise for the Tories in the simple-model projections (uniform change from opinion polls). The Conservative seat forecast is down in both the non-MRP complex models and the MRP average, which is now forecasting just 92 seats for the Conservatives. That average is now based on 9 different MRP models.

Continue reading Fifth combined forecast for the 2024 general election

Breaking the swingometer: historical precedents for proportional change

by Stephen Fisher and Jake Dibden, 26th June 2024

Seat projections for the Conservatives at next week’s general election range from really bad to totally dire. Given recent polls, traditional uniform-change projections suggest the Conservatives will win just around 190 seats. On average the Multilevel Regression and Poststratification (MRP) models suggest the Tories will win less than 100 seats. 

The main difference between them is that the MRP models estimate that the Conservative vote has dropped more where the party was stronger in 2019. That is to say, the drop is broadly proportional to prior strength rather than uniform (the same) across all constituencies.

Some MRP models and other forecasters have come unstuck in the past by predicting proportional change when uniform change predictions have been a better guide to seat tallies for the big parties in the post-war period (see Appendices of the Nuffield Election Studies). The efficacy of uniform change projections was so well established that they became the basis of the swingometer for election night programmes.

Since past vote choice is such a strong predictor of future vote choice, MRP models in effect have a 2019-2024 vote-transition matrix model at the heart of them. That in turn means MRP models tend to project proportional drops for parties in decline. The MRP modellers need a lot of data across constituencies and careful modelling to identify any counter-balancing pattern towards uniform change at the constituency level.

Are we likely to see predictions of proportional change come unstuck again this year? 

Continue reading Breaking the swingometer: historical precedents for proportional change

Fourth combined forecast for the 2024 general election

By Stephen Fisher, John Kenny, Paul Furey, and Polina Ryzhuk. 19th June 2024.

All the different sources still point to a large Labour majority. On average across the different kinds of forecast, the predicted majority is, at 200, up eight from last week. The combined forecast for the Conservatives is down by nine seats, and that for the Liberal Democrats is up by seven seats since last week. Those changes have been largely driven by changes in MRP projections, but other sources have also typically changed in the same direction.

Continue reading Fourth combined forecast for the 2024 general election

Third combined forecast for the 2024 general election

By Stephen Fisher, John Kenny, Paul Furey, and Polina Ryzhuk. 12th June 2024.

All the different sources of seat forecasts still point to a large Labour majority. On average across the different kinds of forecast, the predicted majority is 192, down slightly from 197 last week. The Liberal Democrat forecast has crept up from 36 in our first forecast, to 37 last week, to 41 today. The betting markets are more optimistic for Reform UK winning seats than the poll-based models, as they were last week.

Continue reading Third combined forecast for the 2024 general election

Second combined forecast for the 2024 general election

By Stephen Fisher, John Kenny, Paul Furey, and Polina Ryzhuk. 6th June 2024.

All the different sources of seat forecasts still point to a large Labour majority. On average across the different kinds of forecast, the predicted majority is 197. That is up slightly from the 188 average majority in our first combined forecast this time last week.  

Table 1. Seat Forecasts

Betting MarketsComplex modelsSimple modelsMRPAverage
Con118144195114143
Lab424434392444424
LD4232284537
Reform30011
Green1111
SNP1916132418
PC3333
Lab majority199217134238197

The increase is largely due to the higher Labour forecasts from the MRP models, which are listed in Table 2. They are remarkably different from each other, ranging from a Labour majority of 114 to as much as 324. The forecast number of Conservative seats in the MRP projections range from 66 to 180. A key part of the differences between the MRP projections for the Conservatives and Labour is the degree to which the models expect party performance to be proportional to the prior Conservative vote share. By comparison, traditional uniform change models (under simple models in Table 1) produce more modest forecasts for Labour gains and Conservative losses.

Continue reading Second combined forecast for the 2024 general election