UK General Election BBC Exit Polls Forecast Accuracy
ElectionOracle / UK General Election Jun 08, 2017 - 06:55 PM GMTOver 50,000 polling stations are open today across the UK to cope with the expected demand from an estimated 32 million voters out of a total of approx 47 million eligible to vote. With all eyes turned to the next big event of election night, the BBC EXIT POLL to follow within minutes of the polls closing at 10pm. Which unlike the multitudes of daily opinion polls that have been all over the place for the past month, the exit poll should provide an accurate gauge of what is the probable outcome of the general election some 6 hours before enough seats have been counted to make the actual result clear.
Exit Polls Accuracy:
2016 EU Referendum exit poll vs actual outcome:
- REMAIN 52% / 48%
- LEAVE 48% / 52%
2015 General Election exit poll vs actual outcome:
- Conservative 316 / 331 (-15)
- Labour 239 / 232 (+7)
- Lib Dems 10 / 8 (+2)
- Others 85 / 79 (+6)
2010 General Election exit poll vs actual outcome:
- Conservative 307 / 307 (0)
- Labour 255 / 258 (-3)
- Lib Dems 59 / 57 (-2)
- Others 29 / 28 (+1)
2005 General Election exit poll vs actual outcome:
- Conservative 209 / 198 (+11)
- Labour 356 / 356 (0)
- Lib Dems 53 / 62 (-9)
- Others 28 / 30 (-2)
2001 General Election exit poll vs actual outcome:
- Conservative 177 / 166 (+11)
- Labour 408 / 413 (-5)
- Lib Dems 44 / 52 (-8)
- Others 30 / 28 (+2)
The BBC and other broadcaster pollster based exit polls proved very accurate for the 2001, 2005 and 2010 general elections in determining the outcome in terms of which major party would form the next government, which also proved far more accurate than the opinion pollster forecasts such as that of the US election forecasting guru Nate Silver who got the 2015 UK general election badly wrong as I covered at then time - Nate Silver UK General Election Forecast 2015 as Wrong as 2010?.
However the BBC exit poll for 2015 was very badly wrong as it forecast a hung parliament when the result was for a Conservative outright election victory. And even worse was to come for the EU Referendum, though there it was not really an exit poll rather YouGov's last throw of the dice that got the result very badly wrong with all hell breaking loose on the financial markets shortly after midnight as the actual results were pointing in the exact opposite direction.
So in conclusion expect tonight's BBC exit poll to be out by about 10 seats for the Tories, i.e. if the BBC Exit poll is 340 then the actual result would be closer to 330 or 350. Which in terms of my forecast of 358 in this example the BBC would be under estimating the actual outcome.
Election 2017 Forecasts
The 2017 General Election has proved to be one of the most volatile elections in terms of the polls for decades, which has seen the opinion polls based forecasters literally playing pin the tail on the donkey since Theresa May called the BrExit election. Virtually all of the pollsters started the campaign by forecasting a Tory landslide Conservative election victory of over 400 seats that mostly persisted until barely to 2 weeks ago as the following table illustrates:
UK General Election Forecasts - May 2017
Forecasts | Date | Tory | Labour | Lib | SNP |
YouGov | 16th May | 361 |
213 |
||
Lord Ashcroft | 12th May | 412 |
|||
Electoral Calculus .co.uk | 5th May | 404 |
171 |
8 |
45 |
Election Forecast .co.uk | 10th May | 411 |
158 |
8 |
53 |
Forecastuk.org.uk | 10th May | 383 |
183 |
8 |
52 |
Spread Betting Markets (IG) | 12th May | 397 |
160 |
Whilst I repeatedly reminded that the pollsters had been consistently wrong for every major election since 2010 and that it was highly probable that they were wrong again as illustrated by my following video:
And where subsequently the pollsters have exhibited extreme volatility in their poll numbers that has translated into a forecast of seats range for the Tories from 302 to 420. Whilst here are the final seat forecasts just prior to today's vote, including my own based on the sum of my analysis of the past 6 weeks and separately based on my house prices based forecast which proved by far the most reliable forecaster for the outcome of the 2015 General Election.
UK General Election Final Forecasts
Forecasts | Date | Tory | Labour | Lib | SNP |
Nadeem Walayat - Forecast Conclusion | 4th June | 358 |
212 |
12 |
46 |
Nadeem Walayat - House Prices | 3rd June | 342 |
|||
YouGov | 7th June | 302 |
269 |
3 |
48 |
Lord Ashcroft | 6th June | 357 |
|||
Electoral Calculus .co.uk | 6th June | 361 |
216 |
3 |
48 |
Election Forecast .co.uk | 6th June | 375 |
198 |
8 |
36 |
Forecastuk.org.uk | 6th June | 350 |
225 |
8 |
44 |
Spread Betting Markets (IG) | 7th June | 371 |
199 |
12 |
46 |
BBC Exit Poll - 10pm | 8th June | ||||
Actual Result - 3am | 9th June |
As is usually the case most of the pollsters tend to cluster around one another, and where the betting markets just tend to follow what the pollsters are implying in terms of polling percentages converted into seats. The only real outlier for this election is YouGov which has consistently been discounting the Tory seats total by about 50 to 60 seats compared to the other polls based seats forecasts.
But YouGov being YouGov always slip in a get out of jail card for apparently they have TWO forecasts posted on their site at the same time, one as stated above and another posted just a few hours before the polling stations opened stating that they expected the Tories would be be returned with an increased majority. Which once more illustrates the point that pollsters such as YouGov are bullshit artists! How can anyone make an informed decision based on the pollsters if they are forecasting two significantly different outcomes at the same time!
Whilst here is the analysis towards my forecast conclusion which unlike YouGov did actually correctly forecast the outcomes of the UK 2015 general election, EU referendum and Trump!
So in summary my UK General Election 2017 forecast conclusion is for the Conservatives to win the election with a 66 seat majority by increasing their seats total from 331 to 358. Whilst I expect Labour to drop 20 seats to 212 with the Lib Dems gaining 4 to 12, and I expect the SNP to lose 10 seats, dropping from 56 to 46.
And it won't be long before the BBC's exit poll gives an strong indication of what the result could be.
By Nadeem WalayatCopyright © 2005-2017 Marketoracle.co.uk (Market Oracle Ltd). All rights reserved.
Nadeem Walayat has over 25 years experience of trading derivatives, portfolio management and analysing the financial markets, including one of few who both anticipated and Beat the 1987 Crash. Nadeem's forward looking analysis focuses on UK inflation, economy, interest rates and housing market. He is the author of five ebook's in the The Inflation Mega-Trend and Stocks Stealth Bull Market series that can be downloaded for Free.
Nadeem is the Editor of The Market Oracle, a FREE Daily Financial Markets Analysis & Forecasting online publication that presents in-depth analysis from over 1000 experienced analysts on a range of views of the probable direction of the financial markets, thus enabling our readers to arrive at an informed opinion on future market direction. http://www.marketoracle.co.uk
Disclaimer: The above is a matter of opinion provided for general information purposes only and is not intended as investment advice. Information and analysis above are derived from sources and utilising methods believed to be reliable, but we cannot accept responsibility for any trading losses you may incur as a result of this analysis. Individuals should consult with their personal financial advisors before engaging in any trading activities.
Nadeem Walayat Archive |
© 2005-2022 http://www.MarketOracle.co.uk - The Market Oracle is a FREE Daily Financial Markets Analysis & Forecasting online publication.