UK General Election Prediction
I wrote a week or so ago about using some statistical methodology to try and predict the forthcoming General Election in the UK. I’ve now undertaken my first run of the model I developed and the results are below.
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.
Remember, 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.
Initial Prediction
The following table is the mid-point prediction – i.e. of the 2,000 simulations this is the most likely outcome.
| Party | Vote % | Seats | Prediction Range (95% CI) |
|---|---|---|---|
| Conservatives | 37.3 | 332 | 311 – 343 |
| Labour | 31.3 | 262 | 233 – 290 |
| Liberal Democrats | 16.1 | 13 | 7 – 21 |
| UKIP | 3.9 | 0 | 0 |
| SNP/PC | 2.9 | 20/4 | 9 – 40 / 2 – 7 |
| Others | 8.5 | 19 | n/a |
Other specific predictions
| Conservative Overall Majority | 73.4% |
| Conservative Minority | 25.8% |
| Exact Seat Tie Con / Lab | 0.3% |
| Labour Minority | 0.6% |
| Most Seats in Scotland – Labour | 62.2% |
| Most Seats in Scotland – SNP | 36.8% |
| Most Seats in Scotland – Tie | 1.0% |
I need to do some more work on the Scottish component of the model as I suspect it is over-predicting the SNP share. I will therefore try and get some more data on Scottish polling and see if I can forecast the move from polls to outcome in that area.
Two problems with this:
1. I don’t think extrapolating from
past experience works for UKIP in this cycle. We’re seeing a genuinely
new phenomenon here. The Murdoch press and Mail turned on UKIP quite
some months ago, for example, and it hasn’t impacted on their poll
ratings at all. They’ve also been riding high in the polls for several
years. I just can’t see them doing remotely as badly as 4%. I think
we’re also seeing an early example of the gathering political
irrelevance of the once feared national press; the readership of daily
newspapers has collapsed.
2. I think you’re both too optimistic
AND too pessimistic on the LibDems. I think in terms of share of the
vote, again, your model may not hold up. In past election cycles, the
LibDems got very little coverage between elections and then a sudden
boost in publicity once rules on proportionate coverage kicked in
shortly before election day, and their share of the vote traditionally
followed that. That hasn’t been true over the past cycle and they have a
record in government to defend. On the other hand, they are much better
at gaining and, particularly, defending seats than they once were. If
they got the 16%, most observers belive they’d be looking as 2 or 3
times the number of seats you’re predicting. I think they’ll be
massacred in their Labour leaning marginals but might end up holding on
to a lot of the Tory leaning ones. Eastleigh showed that whatever
hardcore Labour cyberactivists and journalists think, average Labour
voters are still prepared to vote tactically.
Final point – I
think this is a unique election cycle and might even be the start of the
breakdown towards a new balance of parties. The UKIP surge, like the
LibDem boom and bust in 2010, show a huge degree of volatility in the
electorate; the corrosive anti-politics mood is no secret and
potentially quite dangerous. It’s also pretty widespread in the West at
the moment. Predictions are difficult. Remember, some polls have UKIP
breathing down Labour’s neck to top the poll in the Euros, others have
the Tories seeing them off comfortably and pushing them into 3rd place.
People
who say they’re going to vote UKIP almost universally reckon Farage is a
plonker, and they don’t care, they just want so shy a coconut at the
system. You might also be interested in this blog on UKIP I wrote a year
or so ago after Eastleigh
http://sluggerotoole.com/2013/03/07/ukips-voters-older-more-male-and-more-working-class-but-especially-older/
and this one about 18 months ago
http://sluggerotoole.com/2012/11/28/a-ukip-breakthrough-in-2015/
Um :-).
Suspect that – for voteshare at least – this is slightly like predicting who will be King of England in 1067 by studying the family tree of Edward the Confessor.
There are at least two major, and potentially seismic, factors:
1 – UKIP + LD major changes.
2 – The Scottish Referendum.
If the separatists succeed there’s the question of what happens to all the Scottish MPs in 2015; both countries will be weaker, but at least we will not be sharing a country with Salmond.
We should expect to see the UKIP poll shares fall as we reach the end of the year (and correspondingly the Lib Dem ratings rise). If that doesn’t happen then at that point we are looking at the new paradigm you are suggesting.