This is the latest of our forecasts for the UK General Election in 2015. To see our methodology click here. To read a note on our updated forward looking projection methodology, click here.
Forecast
Our mid point and confidence interval forecast for seats is as follows.
| Party | Seats – Mid Point | Seats 50% CI | Seats 95% CI |
|---|---|---|---|
| Conservatives | 299 | 291 – 305 | 268 – 317 |
| Labour | 292 | 281 – 301 | 260 – 314 |
| Liberal Democrats | 13 | 8 – 16 | 6 – 22 |
| UKIP | 2 | 0 – 13 | 0 – 55 |
| SNP | 20 | 14 – 31 | 8 – 46 |
| PC | 3 | 2 – 4 | 1 – 4 |
| Others inc. Green (GB) | 3 | 2 – 4 | 0 – 10 |
| Irish | 18 | n/a | n/a |
Our mid point and confidence interval forecast for votes (mainland GB) is as follows.
| Party | Vote% – Mid Point | Vote% 50% CI | Vote% 95% CI |
|---|---|---|---|
| Conservatives | 33.4 | 32.5 – 34.4 | 30.4 – 36.3 |
| Labour | 31.7 | 30.4 – 32.9 | 28.5 – 35.2 |
| Liberal Democrats | 11.2 | 10.4 – 12.1 | 8.8 – 13.7 |
| UKIP | 13.4 | 10.6 – 16.5 | 5.1 – 22.0 |
| Green | 5.5 | 4.1 – 6.8 | 1.4 – 9.7 |
Our probability of different outcomes is as follows.
| Event | Probability |
|---|---|
| Conservative Majority | 0.2% |
| Conservative Minority | 61.6% |
| Exact Tie Labour and Conservative | 1.9% |
| Labour Minority | 36.3% |
| UKIP more votes than Liberal Democrats | 67.6% |
| Greens more votes than Liberal Democrats | 2.3% |
| Greens more votes than UKIP | 3.6% |
| Green > LD > UKIP (votes) | 0.1% |
| LD > Green > UKIP (votes) | 3.5% |
| LD > UKIP > Green (votes) | 28.8% |
| UKIP > Green > LD (votes) | 2.2% |
| UKIP > LD > Green (votes) | 65.4% |
| UKIP get more votes than Labour | 0% |
| SNP largest party in Scotland (seats) | 29.3% |
What are the main points of your forecast?
We identify the following events / features.
- This has been a much better polling week for the Conservatives and that is reflected in our forecast. As we move into the last 100 days our forecast is affected much more by the volatility of the opinion polls.
- There is now increasing evidence that the Conservative vote is not moving up as we would normally expect in the run up to an Election. This means our expectation of the Conservative’s final position has been dampened. We are seeing some evidence that the Conservative vote is beginning to rise, which might cause us to remove our dampening of Conservative expectations.
- Although the Conservatives lose seats to Labour, Labour lose a significant number in Scotland to the SNP, all but destroying their chance of a workable plurality.
- The Liberal Democrats will struggle to poll significantly above 11%. This will have a dramatic effect on their attempts to retain seats, even with the enhanced Liberal Democrat incumbency effect.
- The SNP are set to at least double their seats in Scotland. If they maintain their current poll rating up to the General Election (at the moment we are expecting the SNP support to fall back in the next few months) we expect them to even outperform Labour on polling day in Scotland.
At the moment we are weighting down the current surge in SNP support. There is evidence that the SNP surge is beginning to dampen, but there is very little historic Scottish specific polling data on which to model SNP movement before an election. This adds to the level of uncertainty to our prediction.
- UKIP support is beginning to drop off, but our confidence interval values indicate that they still have potential to capture a number of seats. Our analysis shows that as the level of support for the Conservatives drops to around 30%, UKIP become significant challengers in many seats, even if they poll less than 20% national share.
- Wales – We have improved our modelling for Wales and this is reflected in the figures above.
The key aspect of our forecast is uncertainty. When the levels of support for the two main parties drop to around and below 30% each, the variability of scenarios increases. We forecast 2 UKIP seats, but the reality is that it is very hard to accurately assess the chances of UKIP in up to 50 seats.
What improvements are you hoping to implement next?
At the moment the model isn’t taking into account polling in individual seats. As such data becomes richer and more available we will attempt to use it.