Issues & Ideas | 7th April 2015

Election 2015: New academic forecast predicts Labour win most seats and take power

With the polls now tied, a new academic forecast gives Labour a slender 5-seat lead, down from a 20-seat lead last month.

Photo: Getty


Who will win the next election, now only a month away? Last month we launched the Polling Observatory election prediction, a new academic forecast to complement the five that May2015 track every day. Our maiden forecast, based on polling through February, predicted a 20-seat Labour victory.

Today we launch our latest forecast, which takes into account opinion polls during March. At the time of our last prediction, Labour were marginally ahead in the polls. Since then, we think the Conservatives have gained slightly, as May2015’s Poll of Polls has suggested. Our estimate of party support now puts the Tories on 32.7 per cent (as of March 31st) – exactly the same as Labour.

Our model is a forecast, rather than a ‘nowcast’ like May2015’s or the Guardian’s. We turn current polls into an election day prediction, based on how the polls have shifted a month before election day in the past. By doing so we forecast the Conservatives to win 34.0 per cent of the vote, up 0.3 points on last month, and enough to give them a one-point lead over Labour, who we are predicting will win 33.0 per cent.

We now predict Labour to have a slender five seat lead on election day.

As a result, Labour lose nine seats, falling from 285 to 276, while the Tories gain six seats (reaching 271) and the Liberal Democrats – who have stopped slipping in the polls and we now predict will win 9.9 per cent on May 7 – are up three in a month (putting them on 27).

This gives Labour a slender five seat lead. None of the other five forecasts on May2015 puts Labour in front (although the Guardian puts the parties within a seat of each other).

Screen Shot 2015-04-07 at 13.48.57

These round numbers mask considerable uncertainty. Our predictions for the two main parties range about 25 seats either way. In order words, it’s possible that the Tories end up with as few as 244 and Labour as many as 302. Alternatively, Labour could win only 252 and the Tories 298.

Labour—276 (252-302)
Tories—271 (244-298)
SNP—49 (35-56)
Lib Dems—27 (21-34)
Ukip—3 (1-4)
Others—6 (4-8)

So who takes power?

The shift in our projected seat totals away from Labour and towards the coalition parties does nothing to make post-election arithmetic any simpler.

The likeliest Conservative-led combinations – where the Tories partner with the Liberal Democrats, DUP and UKIP – still fall well short of the 323 votes needed to win a confidence vote.

Our projected numbers would leave the Conservatives with few options for forming a government, unless Nicola Sturgeon’s alleged interest in a further period of Conservative rule proves to be more than loose talk.

The vehement SNP reaction to the Sturgeon leak confirms that they will be much more comfortable propping up a Labour government than a Conservative one – and with the Scottish nationalists on course for nearly 50 seats, this gives Labour a strong advantage on May 8.

It will be risky for Labour to rely on the SNP alone. Based on our numbers, a Labour-SNP arrangement would command exactly half of the votes in the Commons. It could only succeed if both parties achieved perfect party discipline (highly unlikely given the differences between the parties and the behaviour of MPs in recent parliaments).

It will be risky for Labour to rely on the SNP alone.

We therefore expect a government supported by multiple parties. The Lib Dems will have the most MPs to add to any Labour-SNP pact, but Labour’s weak position in the Commons would make it prudent to also seek arrangements with Northern Ireland’s SDLP, Wales’ Plaid Cymru and the Greens (the latter two parties have already been co-operating with the SNP on possible post-election positions).

In 2010, the idea of a “rainbow coalition” of the left encompassing all these parties was briefly considered by Gordon Brown’s advisers, but then rejected as too unwieldy and unstable. As the 2015 election approaches, a similarly messy alliance now appears to be the likeliest post-election outcome.

A note on uncertainty and constituency polling

This election has been characterised by a proliferation of forecasting models, offered up by an array of academics, media outlets and poll-watchers. This reflects the substantial increase in the amount of information that we now have about public opinion – with nearly a dozen weekly polls, Lord Ashcroft’s constituency results, and surveys such as the British Election Study.

This is a good thing – it provides voters and pundits with more information. But it is essential to note not only the headline numbers, but how they are derived and the uncertainty in what they say.

Constituency polls show the Lib Dems and SNP doing better than national polls imply.

One new factor in the 2015 is constituency polls. How do these affect our election forecast? We can answer this by running our forecast without the more than 150 constituency polls carried out by Ashcroft (and the by-elections in Clacton and Rochester & Strood).

Doing so shows that that the main parties are underperforming in Ashcroft’s polls, relative to the national polls.

Both the Tories and Labour win seven seats fewer if his surveys are excluded, while the Lib Dems and SNP benefit, picking up 7 and 5 extra seats if Ashcroft’s polls are added. This is thanks to an incumbency effect for the former and extra swing in Labour heartlands for the latter.

Polling Observatory is the academics Rob Ford, Will Jennings, Christopher Wlezien and Mark Pickup.