General Election Forecast – Update
Last month I shared the first draft of my General Election forward looking forecast for the 2015 vote in the UK. I’ve now updated the model (see below) and publish the latest forecast.
Remember, the model works on the following basis:
- A statistical model that looks at historical trends for each party of the movement of the polls from x months before the election to the actual point of the election
- Multi-variate analysis looking at the spread of the party’s support in the current polls
- Based on 1 and 2, a projection simulation of the actual election next year. I run 2,000 random simulations and analyse the results to produce the results below.
The model is based on the party’s opinion poll support moving as expected before the next General Election. If the support doesn’t move as expected over the next few months then the model will self-correct and respond to the new situation.
Updates – I’ve vastly improved the Scottish component of the model, and I’ve also increased the number of previous elections examined (the model now goes back over 40 years).
Future Improvements – I’m working on including a more accurate Welsh component in the model.
Prediction
The following table is the mid-point prediction – i.e. of the 2,000 simulations this is the most likely outcome.
| Party | Vote % | Vote Range (95% CI) |
Seats | Seats Range (95% CI) |
|---|---|---|---|---|
| Conservatives | 33.0 | 29.3 – 36.9 | 310 | 259 – 343 |
| Labour | 28.9 | 26.2 – 31.9 | 270 | 234 – 316 |
| Liberal Democrats | 17.2 | 15.7 – 18.7 | 27 | 21 – 37 |
| UKIP | 5.4 | 1.3 – 9.4 | 0 | 0 |
| SNP | n/a | 18 | 7 – 39 | |
| PC | 4 | 3 – 5 | ||
| Others | n/a | n/a | 19 | 18 – 19 |
Other specific predictions
| Conservative Overall Majority | 24.55% |
| Conservative Minority | 50.90% |
| Exact Seat Tie Con / Lab | 0.85% |
| Labour Minority | 22.25% |
| Labour Majority | 1.45% |
| Most Seats in Scotland – Labour | 77.1% |
| Most Seats in Scotland – SNP | 21.9% |
| Most Seats in Scotland – Tie | 1.0% |
At the moment the model is predicting a decline in the UKIP vote back to a level slightly higher than the 2010 figure. Looking at the underlying mathematics, if UKIP is maintaining it’s current polling position after the Conference season then it will begin to perform significantly better in the forecast.
I’m going to produce a Point in Time forecast for the Euros shortly.
Relying on old polls is not going to work this time: the political situation is changing fast, as in Holland, where Pim Fortuyn changed the face of a jaded system. UKIP is going to replace the LibDibs as the third party, at the 2015 general election, and the more interesting issue is to what extent it will kneecap many Tory candidates in marginal seats where UKIP does not win but takes enough Tory votes to ensure defeat for the Tory candidates.