Posted by Simon Hix and Nick Vivyan.
We have updated our election prediction model, based on national voting intention results from all polls with fieldwork up to and including 19 April – hence, taking into account the full set of polls after the first TV leaders’ debate. Here is a figure showing the time trends in our “pooling the polls” analysis. The dots in the figure show the results from the various polls and the shaded areas around the lines are the 95 per cent confidence intervals around the mean standings of the parties.
Time trends in Hix-Vivyan ‘Pooling the Polls’ analysis: January – April 2010
As of 19 April, the national standing of the parties was 32.3 per cent for the Conservatives (down 4.2 per cent from our 20 March analysis), 26.8 per cent for Labour (down 3.7 per cent), and 30.1 per cent for the Lib Dems (up 9.9 per cent). Looking across the polls, the performance of Nick Clegg in the TV debate appears to have shifted Lib Dem support upwards by about 9-11 per cent, at the expense of both Conservatives and Labour.
What would these numbers mean in terms of seats in the Commons?
The following table shows how these national vote shares might translate into seats under different assumptions: namely, (1) a uniform change in party support across constituencies, and (2) differential changes in party support in each region of the country, based on the latest regional polling data from YouGov.
Hix-Vivyan Seat Projections for 21 April
Hix-Vivyan pooling-the-polls model | Comparison with other predictions | |||
---|---|---|---|---|
Assuming a uniform national swing | Assuming different regional swings | UK Polling Report Seat Projection | Electoral Calculus Seat Projection | |
Last Checked | 19 April | 19 April | 20 April | 20 April |
Conservatives | 256 | 259 | 296 | 255 |
Labour | 262 | 259 | 237 | 267 |
Liberal Democrats | 110 | 103 | 85 | 97 |
Other Parties | 32 | 29 | 32 | 32 |
No. of seats Cons short of a majority | 80 | 67 | 30 | 71 |
No. of seats Labour short of a majority | 64 | 67 | 89 | 59 |
In other words, if we assume that changes in votes between the parties since 2005 translate more or less uniformly across constituencies, then Labour has a good chance of being the largest party in the Commons, despite trailing the Conservatives by more than 5 per cent in the polls.
However, if the current regional standings of the parties is a better predictor of constituency-level performance in the election, then Labour and the Conservatives could be neck-and-neck in the Commons.
Either way, given the best currently available information about the way parties’ votes are distributed across constituencies, the Lib Dems are likely to be at least 100 seats short of Labour and the Conservatives even if it is a three-way battle in the national polls.
Disappointing to see no consideration of the possibility that the LibDems will surge up *again* after the second debate. How much more of a swing is needed for the LibDems to take the lead? I’d like to see some more sophistacated modelling than “uniform swing” (a particularly poor model for LibDems I gather) too but maybe the regional one is the best we can hope for even though I think the restuls of a seat-by-seat analysis would be interesting and shouldn’t be beyond the abilities of some of the bigger organisations looking at these things.
Despite being on Sky, it is repeated on the BBC and will presumably be available ‘On Demand’ in addition to youtube and all the clips: there should still be a good audience. Furthermore it has always been the case that the LibDems do better in polls that ask “Would you vote for the LibDems if you thought they could win?” A recent poll gave them 49% on that question: there’s plenty of room for the surge to go up rather than down.
…which doesn’t mean that it will of course but if Clegg performs well it’s far from impossible that next week the question will be which party will support Clegg’s minority government and what their demands would be.
When I heard commentators and politicians consistently saying that Brown’s strength is the economy* while Cameron’s strongest message is that he is the man for change**, it seems increasingly likely that the yellow surge will keep on going.
* Brown led us into a bad recession and horrible deficit; PPS, PFIs aren’t even in his debt figures I think; though I’m not sure how big that is.
** shifting back to the party that has governed us for so much of the last century can’t possibly compare to a radical change in the whole system of governement.
Ken Clarke has taken a number of non-executive directorships and engaged in non-political media work, including serving as Deputy Chairman[11] of British American Tobacco (BAT) (1998-2007) and Deputy Chairman of Alliance Unichem, and has faced allegations over the activities of BAT in lobbying the developing world to reject stronger health warnings on cigarette packets and evidence that his corporation has been involved in smuggling and targeting children with advertisements