General Election Prediction

Current Prediction: Conservative short 19 of majority

Party2019 Votes2019 SeatsPred VotesLow SeatsPred SeatsHigh Seats
CON 44.7%365 39.1%215307385
LAB 33.0%203 38.0%185255347
LIB 11.8%11 7.3%3723
Brexit 2.1%0 2.4%002
Green 2.8%1 4.3%111
SNP 4.0%48 4.6%435858
PlaidC 0.5%4 0.5%145
Other 1.1%0 3.8%002
DUP 8  8 
SF 7  7 
SDLP 2  2 
Alliance 1  1 

Prediction based on opinion polls from 05 Nov 2020 to 28 Nov 2020, sampling 12,170 people.

Probability of possible outcomes

Lab minority
Conservative majority
No overall control
Labour majority

The future is never certain. But using our advanced modelling techniques, we can estimate the probability of the various possible outcomes at the next general election. Minority government probabilities assume possible alliances between the Conservative and Brexit parties, and between Labour, Liberal Democrats, SNP and Plaid Cymru.

In the headline prediction table, the columns 'Low Seats' and 'High Seats' give the 90 per cent confidence interval for the number of seats won.

New Boundaries 2023

New Seat Boundaries – Likely Impact

As the Boundary Commissions are about to begin their work on redrawing the Westminster seats, Electoral Calculus has drawn its own (unofficial) example set of seat boundaries to see what might happen. This was done by following the same rules that the Boundary Commissions have to follow, and using the up-to-date ward boundaries from 2020.

Party2019 VotesActual
(old) Seats
(new) Seats
CON 44.7%365380+15
LAB 33.0%203194−9
LIB 11.8%116−5
SNP 4.0%4849+1

Using these example boundaries, Labour loses about ten seats to the Conservatives since Wales and the North of England lose seats, while the South and East of England gain seats. This estimate is more favourable to the Conservatives than our original estimate in March 2020.

Our analysis also creates a way to check that the Boundary Commissions' maps are genuinely fair. Unfair boundaries could move about sixty more seats from one party to another according to our figures, but hopefully the official maps will be closer to the unbiased example than to those extremes.

The Boundary Commissions are expected to finalise their official proposals by 2023.

Read our analysis, along with an interactive map, of the possible new boundaries.

Posted 27 October 2020

Technical statistics paper

Estimating quantiles from biased stratified samples

A technical statistical paper from Electoral Calculus on how to estimate quantiles of distributions from empirical observations. This includes the case, common to market research, where we have a weighted set of observations from a stratified model.

Quantile Estimation: Convergence of local shape parameter

Interestingly, some accurate quantile formulas involve the tail shape parameter ξ which is studied by Extreme Value Theory.

Read "Quantile Estimation" in PDF form.

Posted 17 August 2020

Prediction details

Why is the predicted SNP seat total outside the confidence range?

Puzzlement has swept Scotland since our latest Scottish prediction shows the SNP on course to win 58 seats which is outside the confidence interval of likely outcomes. As many readers have asked, how come?

The answer is interesting, though a little technical. The two numbers are calculated in different ways, and normally the difference is small, but not in the special case of current Scottish politics.

Let's start with the headline Scottish prediction showing the SNP set to win 58 seats. This means that there are 58 seats where the SNP is predicted to have more votes than any other party. This mostly corresponds to seats where the SNP's chance of winning is 50pc or better. In each of these seats, the most accurate prediction is to predict an SNP victory, even if the chance of that is less than 100pc, since that is the most likely outcome.

There is a different approach which is to look at the average number of seats that the SNP might win, allowing for random variations between the Scotland-wide vote and the voting pattern in each individual seat. On that basis, a seat which the SNP are certain to win will score 1.0, but a seat with only a 60pc chance of SNP victory will score 0.6. On that basis, the average expected number of SNP seats is only 44.2.

The confidence intervals are calculated on a similar basis to the average number of seats, and allow for random variation between individual seats and the Scotland-wide picture. The SNP confidence interval is currently 41-57 seats, which includes the average, but does not include the headline prediction.

In turns out that a little bit of randomness is very bad for the SNP. This weakness is a strange consequence of their strength. Since they are predicted to win all but one of Scotland's seats, they don't want anything to change that outcome. Any seat which moves around with random variation increases the risk of an SNP loss. Only one seat (Edinburgh South) could migrate to being an SNP gain, but that is quite unlikely.

Scottish seats by SNP win chance

The graph above shows how this works. Almost all the yellow dots are above the green line, which means that the SNP is predicted to win that seat and its chance of winning is more than 50pc. Only one seat is much below the line, and it is far away. But the SNP is not certain to win all these seats, since many of the win chances are below 75pc. Although the SNP is more likely than not to win each seat, it is very unlikely to win them all. Like playing many rounds of Russian roulette (advisory: don't) you are likely to win any round individually, but unlikely to win every round overall.

Party2019 Votes2019 SeatsPred VotesHeadline
Predicted Seats
Expected Seats
CON 44.7%365 42.7%334316.6
LAB 33.0%203 37.2%229249.7
LIB 11.8%11 7.6%614.9
Brexit 2.1%0 1.2%00.6
Green 2.8%1 3.8%11.6
SNP 4.0%48 4.5%5844.2
PlaidC 0.5%4 0.5%43.0
Other 1.1%0 2.5%00.2

Prediction based on opinion polls from 04 Jun 2020 to 26 Jun 2020, sampling 13,533 people.

Other parties have their own differences between the number of seats which they are predicted to win (the headline prediction) and the average expected number of seats won. Generally the larger parties, such as the Conservatives and the SNP have a better headline prediction compared with the average. Challenger parties, such as Labour and the Lib Dems, do better with the average compared with the headline.

Electoral Calculus uses the headline prediction rather than the average expected number of seats won for three reasons. These are: the headline is more transparent and links directly to the prediction for each seat; it avoids a large dependency on opaque randomness parameters; and it worked well in December 2019.

Posted 9 July 2020

New Wards for Parliamentary Boundary Review

Upgrade to Wards 2020 for Parliamentary Boundary Review

A new update to our electoral geography has upgraded the wards used to be the latest wards in force for 2020. The reason for this is that these are expected to be the wards used as the basis for the upcoming review of parliamentary seat boundaries.

The current draft legislation, the Parliamentary Constituencies Bill 2019-21 (text) instructs the four Boundary Commissions (one each for England, Scotland, Wales and Northern Ireland) to conduct new parliamentary boundary reviews with a "review date" of 1 December 2020, and to complete the review before 1 July 2023.

The new parliamentary seats will be made up of, as much as possible, by joining together groups of (entire) local authority wards. This makes the local authority wards an important part of the new seat boundary process, so Electoral Calculus needs to use the same wards as the boundary commissions.

An innovation in the bill is that the wards to be used are the "local government boundaries which exist, or are prospective, on the review date". This means that the wards used will be similar to the wards of 2020, but will include wards which will change in the next couple of years.

As a first step, the Electoral Calculus electoral data has been upgraded to work with the wards of 2020. These "Wards 2020" are similar to the earlier "Wards 2019" which were incorporated in April, but include changes to these local authorities: Basingstoke and Deane, Buckinghamshire, Cambridge, Chorley, Halton, Hartlepool, Oxford, Pendle, Rotherham, Salford and Stroud. The new unitary authority of Buckinghamshire abolishes the previous district councils of Aylesbury Vale, Chiltern, South Bucks and Wycombe. There are a total of 303 new local authority wards.

An additional complication is that the local elections of 2020 were postponed for a year due to the coronavirus outbreak. This means that there were no, and never have been, local elections in those new wards of 2020. Electoral Calculus has used models to infer the likely result of earlier local elections in those new wards.

Using those data, it is possible to infer the likely result of the December 2019 general election in every ward of 2020. This will be useful when the Boundary Commissions report, in terms of predicting the political composition of each new seat.

Wycombe seat by wards 2020
Boundary Lines courtesy of Ordnance Survey OpenData © Crown copyright 2020, Map © OpenStreetMap contributors

Until then, site visitors are now able to:

Posted 1 July 2020

Ward Boundaries and Local Election Results

Major update to local authority ward data

To keep our electoral geography up to date, Electoral Calculus has completed a major update of its local authority data. Since our last update in 2015, there have been many changes to local council areas, ward boundaries and four year of local election results.

These changes have now been incorporated in our datasets, and are now visible on the website. Maps and ward details now show council ward boundaries as at 2019, and the most recent local election results are used to help infer the general election result in each ward.

Local government changes include the creation of five new councils ('Bournemouth, Christchurch and Poole', Dorset, East Suffolk, West Suffolk, and 'Somerset West and Taunton', and the abolition of 14 councils which lay within the newly created councils.

Additionally, one hundred councils in England and Scotland have had their ward boundaries redrawn by the relevant authorities since 2015. Altogether around 2,800 (30pc) of the 9,200 wards in the UK have been changed in one way or another. These new wards and their boundaries are now included in the Electoral Calculus analysis and maps.

Our thanks to all those people and organisations who have helped with the local election results data. In particular, to Andrew Teale and his Local Elections Archive Project, Democracy Club (UK results), and the many contributors to Wikipedia's local election results pages.

We are also grateful to those official bodies who have made data available: all 382 local authorities in England, Scotland, Wales and Northern Ireland; Office of National Statistics; Ordnance Survey; Local Government Boundary Commission for England; Electoral Commission; Scottish Government Statistics; National Records of Scotland; Northern Ireland Statistics and Research Agency; Electoral Office of Northern Ireland.

Overall the project required around 1.2GB of data split over 1,600 files, thirty spreadsheets, eleven database tables and seven programming languages.

GE2019 result by Wards 2019, London-area detail
Data map of General Election 2019 result by Ward Map © OpenStreetMap contributors

Site visitors are now able to

Posted 24 April 2020

Coronavirus and public opinion

Voters increase trust in government but fear for the economy

The Electoral Calculus poll of polls this month sees the Conservatives with a strong lead of 24pc over the Labour party. This is based on four polls conducted throughout March 2020, which all show the Conservatives with around 50pc national support.

This gain is probably due to changing public attitudes to the government and its key members due to the coronavirus epidemic. Support and confidence in the government has sharply increased as events have escalated and some of that has translated into extra support for the Conservative party.

Opinium conducted two polls this month, both before and after the UK lockdown was announced on 23 March. According to them, the public's net approval of the government's handling of the situation increased from 14pc net approval (total of those approving minus those disapproving) up to 43pc, a gain of 29pc. Trust in Boris Johnson personally increased from −2pc net trust up to +26pc, a gain of 28pc in just two weeks. Those figures are broadly confirmed by a Number Cruncher Politics poll which measured net satisfaction with the government at 47pc, and the same number for satisfaction with Boris Johnson.

Voters' concerns are also reflected, by Opinium, in the net number of those worried about the virus (less those not worried) which rose from 47pc to 75pc during March.

Support for the lockdown measures is very strong, with Opinium measuring a net support of 88pc (with 92pc in favour and 4pc against).

But voters are also fearful for the economy. A net 59pc of voters think the UK economy will get worse over the next year (up from 38pc two weeks before), and a net 30pc of voters think their own personal finances will deteriorate. Strikingly, 24pc of all workers think is it quite likely or very likely that they will lose their jobs due to coronavirus.

In these early stages of the public health restrictions, the government is enjoying strong support and confidence. That will be a useful asset in the longer haul as inevitable frustrations may grow in time. The longer-term political outlook is harder to predict as the political standing of the parties will depend on the course that events take and the public's perception of their actions.

Polling Sources

Posted 31 March 2020

New Parliamentary Boundaries 2020

Government announces plans for new boundaries with 650 seats

In a quiet written statement this week, the government announced that it is going to restart the stalled programme of new boundaries for Westminster constituencies. This new review, which is yet to be legislated for, will keep the number of seats at 650 and not reduce them to 600 as had been planned by David Cameron's coalition government.

But the boundary review is likely to require new seats to be nearly identical in terms of the number of electors in each seat. The previous review had a very strict limit, and required each new seat to have an electorate which was not further than 5pc lower or higher than the average.

The previous legislation also specified that further new boundary reviews would take place every five years. This week's statement changes that period to every eight years, allowing for two Westminster elections to take place using each set of boundaries.

The current boundaries were first used in 2010 (and 2005 in Scotland), and are now getting a little out of date. Regular boundary reviews are an established part of the electoral process and a new review would be due around now in any case. The reviews are conducted by the four independent Boundary Commissions for England, Scotland, Wales and Northern Ireland and involve periods of public consultation.

Electoral Calculus has made a initial approximate estimate of the possible effect of these changes.

2019 SeatsEstimated
New Seats

The average electorate over all seats in December 2019 was 73,211. But this conceals some wide variations. The average electorate of a seat won by Plaid Cymru in Wales was just over 50,000 voters. And the average electorate of a seat won by the Conservatives was over 74,500 voters, which is nearly 50pc larger. The average electorates of Lib Dem, SNP and Labour seats are also lower than average. These facts provide some support for the Conservatives' arguments that the boundaries could be made more fair.

Our approximate calculations suggest that the Conservatives could gain about half-a-dozen seats from a new review, at the expense of Labour and the nationalist parties in Scotland and Wales. This could increase the Conservative parliamentary majority from 80 to 92.

The disparity between seat sizes can also be seen at a regional level.

2019 SeatsEstimated
New Seats
North East67,1372972,11027−2
West Midlands71,3755973,87957−2
North West71,6907573,65473−2
Northern Ireland71,8871871,887180
East Midlands75,7214674,11047+1
South West77,0735573,08758+3
South East78,9348472,86291+7

The table above shows the current average electorates for each of the twelve regions of the country along with their current number of parliamentary seats. If the seats were all standardised to be of equal size then the number of seats would change. The table shows that Wales (particularly), Scotland and the North and West Midlands of England are currently over-represented and need to lose seats. Conversely, London and the South and East of England are under-represented and need more seats. Since the latter group is more Conservative-leaning than the former, the Conservatives tend to benefit from this correction.

Technical note: the above analysis assumes that four island seats (Orkney and Shetland, Western Isles, and two Isle of Wight seats) will be protected and kept as individual seats despite being under-quota. This requirement was in the original legislation.

Posted 27 March 2020

Comparison of our final prediction with the election outcome

PartyEC Pred
EC Pred

The actual election outcome is shown above side-by-side with the final Electoral Calculus prediction. The Speaker is taken as Labour. Note that vote shares are given on a GB basis (excluding Northern Ireland). On a UK-wide basis, the Conservatives got 43.6% and Labour got 32.1%.

The polling error was relatively small, with the estimated Conservative lead of 9.4pc being close to, but lower than, the actual lead of 11.7pc.

A rule of thumb is that a prediction is pretty acceptable if the seat error for the major parties is within twenty seats. For the Conservatives, the prediction error was 14 seats and for Labour it was 21 seats, which seems a fair result.

This seems a good practical illustration of the ability of regression-based polling analysis, which can be effectively done with moderate sample sizes, and which Electoral Calculus has pioneered.

It also provides a welcome relief to the polling industry overall, which had a relatively good performance, after several years of disappointing results.

Full analysis of the prediction performance at 2019 is here.

Posted 13 December 2019

Prediction Performance Analysis

How accurate were our predictions?

Electoral Calculus predicted the national vote share for the parties, the total seats they would win and the result in every UK constituency.

This year our predictions were fairly accurate, partly due to our new regression-based model. Our predictions were also more accurate than any other pre-poll predictor from other organisations.

Our traditional post-election analysis looks at exactly what we got right, and what, if anything, went wrong.

See the full track record for 2019, and the overall summary of our track records since 1992 which shows that we often get it about right, but not always.

Posted 27 January 2020

Tactical Voting

Stalemate between pro-Remain and pro-Leave tactical voters

Unique analysis by Electoral Calculus shows that tactical voting was quite prevalent at the December 2019 election. Both pro-Remain and pro-Leave voters were capable of voting tactically to support their second choice candidate and keep out their rivals. Up to 50pc of third-party supporters were prepared to change their vote in this way.

Many seats saw large tactical swings, and became more marginal, but few seats actually changed hands due to tactical voting. Our estimates show that about ten seats were gained by non-Conservative pro-Remain parties due to tactical voting, and about the same number were gained by the Conservatives thanks to pro-Leave tactical voting. The net result was a tactical stalemate, with no decisive advantage to either side.

See the full details, including our unique interactive tactical triangle graphic which classifies seats by their tactical voting behaviour.

Pro-Remain Tactical Voting in 2019

This configuration of the interactive tactical triangle shows those seats which saw strong pro-Remain tactical voting. Each seat is represented by a yellow stalk which shows the difference between the expected result in the seat and its actual result (marked by a dot coloured for the winning party). These seats move in the direction of the orange arrow (if the Lib Dems are stronger) and parallel to the red arrow (if Labour are stronger). Many seats get closer to the dotted lines (meaning they become more marginal), but few cross the dotted lines (where the seat changes hands).

See the full interactive graphic only on Electoral Calculus, including changed seats and full explanations.

Posted 12 February 2020

Voter Migration by Seat

See how every seat swung at the 2019 election

This triangular viewpoint shows every seat and how it moved politically from 2017 to 2019. Each party has a corner of the triangle representing 100pc support for that party, and the party wins those seats that end up closer to its corner than the others. The stalk of a seat shows the political distance travelled, and its blob represents the 2019 result in that seat.

Read details.

The triangle shows a swathe of seats swinging from Labour to Conservative, and another group of Conservative seats moving up towards the Liberal Democrats, but with few seats actually changing hands.

See the full graphic only on Electoral Calculus, including changed seats and full explanations.

Posted 22 January 2020

Voter Migration by Group

Working class swung away from Labour but youthful right-wingers went a bit Lib Dem

All new analysis of voter migration by political and demographic group is now available. See how voters in the seven Electoral Calculus tribes changed their votes and see how Brexit attitudes trumped economic concerns at this election. Also includes how demographic characteristics like age can strongly influence people's votes. Read details.

Swings from 2017 to 2019 by Tribe

Read the full analysis only on Electoral Calculus.

Posted 21 January 2020

Voter Migration by Party

Labour lost voters and the Conservatives kept theirs

The Electoral Calculus voter migration graphic has been updated for the recent election. An important feature this year were the voters who abstained from voting, particular Labour leavers. Also notable was the success of the Conservatives in keeping their voters loyal, even the Remainers. Read details.

Read the full analysis only on Electoral Calculus.

Posted 16 January 2020

Prediction review

Boris was the Conservatives' secret weapon

Much of the post-election analysis has focused on the perceived defects of the Labour campaign and Jeremy Corbyn personally. Less remarked upon has been the remarkable popularity of Boris Johnson. Johnson significantly outscored Corbyn in polling on who would be the best Prime Minister. But he also achieved an instant and significant turnaround in the fortunes of the Conservative party.

The graph below shows the monthly Electoral Calculus seat predictions since the previous election in 2017. Under Theresa May, the Conservatives were never predicted to win a parliamentary majority (with one narrow exception in February 2019). Once Boris Johnson took over on 24 July, the Conservatives were never predicted to be short of a majority.

Predicted Seats since June 2017

We can explore the details of what happened in this eventful year, by looking at some key political dates. The table below shows those key dates, along with the opinion poll lead of the Conservatives over Labour, the Electoral Calculus seat prediction, and the predicted Conservative majority.

DateEventCon-Lab leadCon seatsCon Maj
03 Jun 2019Euro Election aftermath-4%54n/a
12 Jun 2019ComRes/Telegraph hypothetical poll15%395140
02 Sep 2019Polling after Boris Johnson becomes PM8%35662
30 Oct 2019Start of campaign10%36376
30 Nov 2019Campaign high for Labour as Lib Dems squeezed8.5%33622
12 Dec 2019Final Electoral Calculus prediction9.5%35152
12 Dec 2019General election outcome11.5%36580

Following the Euro elections in May, the Conservatives polling at the end of the month was dreadful. They were on 19pc, while Nigel Farage and the Brexit party were ahead of them on 24pc. An election at that moment could have seen the Conservatives almost wiped out and reduced to around 50 seats in the House of Commons.

Whilst the Conservative leadership campaign was in full swing, there was a ComRes/Daily Telegraph poll on 12 June which asked the hypothetical question of how people would vote if Boris Johnson became Prime Minister. The poll showed a Conservative lead of 15pc which Electoral Calculus converted into a Conservative majority of 140 seats. This analysis was widely dismissed as unrealistic at the time by a professor of politics ("bulls••t"), the Guardian ("Theresa May was going to get a landslide too...") and the BBC's Laura Kuenssberg ("treat with... a bucket of salt"). Although the poll was not a precise prediction of events to take place six months later, it was broadly accurate in forecasting a complete turnaround in Conservative fortunes and a large Conservative majority under Johnson.

Once Johnson became Prime Minister, the next Electoral Calculus poll-of-polls at the end of August had the Conservatives 8pc ahead of Labour, and predicted to get a majority of 62 seats. This was the first time since the previous election that the Conservatives had been predicted to get a working majority from voting intention polling.

Two months later, at the start of the election campaign at the end of October, the Electoral Calculus poll-of-polls showed a Conservative lead of 10pc over Labour and a majority of 76 seats. This followed the Conservatives successful squeeze on Brexit party supporters as Boris Johnson indicated he was serious about achieving a Brexit deal.

The Labour party hit their high point around the middle of the campaign in late November by squeezing Liberal Democrat supporters. The Electoral Calculus poll-of-polls at the end of November showed a Conservative lead of 8.5pc over Labour and a smaller Conservative majority of 22 seats.

The final campaign prediction from Electoral Calculus was published early on election day. Using our latest regression-based seat-by-seat predictions, our poll-of-polls showed a Conservative lead of 9.5pc giving them a majority of 52 seats. The actual election result had a Conservative lead which was 2pc higher at 11.5pc, and with a few more seats as a consequence. If the pollsters' accuracy had been completely precise, rather than just very good, then our seat predictor would have predicted a majority of 74 seats.

Before this year, Boris Johnson had built up a reputation as an election winner. Winning twice as Mayor of London in a Labour-leaning city was proof that he could reach more parts of the electorate than Conservatives normally could. In the leadership contest, Conservative MPs and members judged that he could do the same at the national level. That judgement has been vindicated by all the polling since his selection and especially by the general election result.

Posted 20 December 2019

Election data

Election results in geographic detail

The Electoral Calculus has now been updated with detailed data of the 2019 election result. Available features include:

Seat details example - Somerset North East Seat details pages now show the actual election result compared with our prediction, so you can see how accurate we were in each seat (spoiler: we got the winner right in 605 out of 650 seats).

It also shows the party winner at the the last three elections, and gives a map of the seat with the estimated winner in each ward at the 2019 election.

Postcode level data example Results have been estimated at ward and street level using our proven regression-based techniques. See how your own neighbourhood voted by entering your postcode.

Browsable seat map - North East detail The browsable seat map has been updated to show the new results, giving a graphical view of the election result.

And you can click on any seat to view the seat in detail.

Our data map has also been updated to show the 2019 result, as well as the 2017 and 2015 results. Clicking from one view to another gives a way of seeing how political opinion has moved over the last four years.

Also newly available are estimates of social attitudes (from liberal to conservative), and the Electoral Calculus tribe identity.

The map can show results at seat level, ward level, or street (output area) level.

Posted 19 December 2019

New Boundaries

New Boundaries give Conservatives 104 seat majority

Electoral Calculus has projected the result of the 2019 election onto the new constituency boundaries proposed by the Boundary Commissions in 2018.

PartyActual general
election result 2019
Implied result at 2019
under new boundaries

The projection gives the Conservatives a majority of 104 in the new 600-seat parliament, with the party winning 352 seats. The Labour party is projected to win fewer than half that number, only winning 174 seats. Many of the smaller parties lose a few seats with the Liberal Democrats predicted to gain as many seats as the DUP and Sinn Fein.

See which new seat you will be in by entering your postcode:   

Note that the government may or may not press ahead with new constituency boundaries. If they did, they might either use the 2018 proposals, or they might ask the Boundary Commissions to refresh the proposals. They might continue the plan to shrink parliament to 600 seats, or they might retain the current 650 seats. In any event, it should be expected that the Conservatives would benefit from a boundary review since the smaller seats tend to be in Wales and the North where Labour is stronger.

See the full details on our new boundaries page or in our browsable new seat map.

See also today's story in the Daily Telegraph.

Posted 19 December 2019

Prediction analysis

Seat predictor accuracy

The final Electoral Calculus prediction is made up of two components: the poll of opinion polls and the seat predictor. Both parts performed well.

The poll-of-polls showed a Conservative lead over Labour of 9.4pc compared with an actual lead of 11.7pc. The difference between those, an error of 2.3pc, is low by historical standards. The equivalent lead errors were significantly higher in recent elections, with an error of 4.3pc in 2017 and a large error of 6.3pc in 2015.

Even with the poll error, the seat predictor performed very acceptably. The two major parties were within the margins of error, and the Conservative prediction of 351 seats was only 14 seats too low. Of all major UK seat predictors in 2019, the Electoral Calculus final prediction came closest to the actual result. Other predictors generally had the Conservative seat prediction too low, such as FocalData (337 seats), YouGov (339 seats) and Datapraxis (344 seats).

Of course, there is more to prediction accuracy than the headline seat count, since every seat is predicted individually which provides 650 opportunities to be right or wrong. Looking at the final Electoral Calculus seat-by-seat prediction, the winner was predicted correctly in 605 seats and incorrectly in 45 seats. That is a success rate of 93pc, which is the same as the high success rate of YouGov's final large-scale MRP in 2017. About a third of the incorrect seats were marginals which could have gone either way, leaving 31 seats which were mis-predicted.

We can also separate out the errors caused by polling and by the seat predictor. If we feed the actual national vote shares for GB and Scotland into the Electoral Calculus seat predictor we get the following result:

EC Pred

You can see this for yourself by running the seat predictor with the correct national and Scottish vote shares: run predictor.

This is quite an accurate performance, with all parties correctly predicted to within just three seats. As it happens, this is as accurate as the TV Exit poll.

Of the two causes of error: polling error and predictor error, the polling error was actually the larger component, even though it was fairly small. The error in the prediction model was quite small indeed.

Posted 16 December 2019

Election Results flat file

Election Results 2019 in a single file for download

Many people are interested in a single file which contains all the constituency results in one place. This is now available for download as an Electoral Calculus flat file (53k).

The data format is explained on the Historical Data page.

Please note this is a first draft which has been prepared rapidly and not cross-checked. Please let us know if you see any errors or omissions.

Posted 16 December 2019

Final Prediction: Conservative majority 52

Party2017 Votes2017 SeatsPred VotesLow SeatsPred SeatsHigh Seats
CON 43.5%318 43.3%307351398
LAB 41.0%262 33.9%178224264
LIB 7.6%12 11.7%121328
Brexit 0.0%0 3.2%001
Green 1.7%1 2.7%011
SNP 3.1%35 3.6%284144
PlaidC 0.5%4 0.4%024
UKIP 1.9%0 0.0%000
Other 0.7%0 1.1%002
DUP 10  10 
SF 7  6 
SDLP 0  2 
NI Other 1  0 

Prediction based on opinion polls from 04 Dec 2019 to 11 Dec 2019, sampling 23,869 people.

Probability of possible outcomes

Conservative majority
No overall control
Lab minority

The future is never certain. But using our advanced modelling techniques, we can estimate the probability of the various possible outcomes at the next general election. Minority government probabilities assume possible alliances between the Conservative and Brexit parties, and between Labour, Liberal Democrats, SNP and Plaid Cymru.

In the headline prediction table, the columns 'Low Seats' and 'High Seats' give the 90 per cent confidence interval for the number of seats won.

Electoral battleground

Electoral battleground update

This revised version of the battleground (originally from 11 December) has now been amended to show the actual election result of Conservative 44.7pc and Labour 33.0pc. The actual result is marked by a yellow dot.

Electoral Battleground with 90pc confidence area, plus result

The actual result is well within the 90pc confidence area (red oval), which shows that the polling industry had a fairly accurate performance this year, with many pollsters being quite close to the actual result.

Posted 13 December 2019

Electoral battleground

Electoral battleground and confidence areas

This graphic shows the electoral battleground as a two-dimensional map. The horizontal x-coordinate, or longitude, is the possible Conservative vote share running from 25pc to 50pc, and the vertical y-coordinate, or latitude, is the possible Labour vote share which goes from 20pc to 45pc.

Electoral Battleground with 90pc confidence area

Using the Electoral Calculus seat predictor, we can convert the Conservative and Labour vote shares into seats (assuming the other parties gain and lose votes in proportion to their current vote shares). These seat predictions can then be categorised into zones depending on the overall parliamentary result. The main categories are: Conservative majority government, Labour majority, Lib Dem majority, Labour minority government, or a hung parliament in which there is no obvious majority coalition. The chance of a minority Conservative government is vanishingly small because the Brexit party has faded and the DUP seem unlikely to reforge an alliance with the Conservatives.

The current Electoral Calculus poll-of-polls is marked with a red dot labelled "We are here", and various recent polls are marked by green dots. The slanted red oval, which is actually an ellipse, is the 90pc confidence area for the actual election result. In other words, it is pretty likely that the actual election result will be somewhere inside the red oval. The oval is centred on the poll-of-polls but has sufficient size to include all the various pollsters, plus a little extra. Experience has shown that the pollsters are not always correct, so margin has been left for polling error.

Although the central case is for a moderate Conservative victory, other outcomes are possible. The oval clearly extends into the hung parliament zone and nearly touches the edge of the Labour minority government. At its other extreme, the confidence oval reaches deep into Conservative majority territory and includes a landslide Conservative majority of 224 seats.

The main outcomes which look unlikely to happen are any majority government by a non-Conservative party. But otherwise, the other options are all (just) possible.

Posted 11 December 2019

Political Analysis

Three-D Politics and the Seven Tribes

A major new piece of analysis by Electoral Calculus and pollster ComRes creates a three-dimensional landscape of British politics and identifies the seven political tribes which occupy it.

Electoral Calculus has moved beyond a simplistic one-dimensional view of politics, and even gone further than our own pioneering two-dimensional view, to create a three key dimensions of political attitudes:

Using major polling work by the British Election Study, we can give a political three-D position for each poll respondent identifying their political position on each of the three dimensions.

Groups of like-minded individuals can be spotted to identify seven political tribes of people with similar political attitudes, and gain insight about their demographics and voting behaviour.

3D Politics Tribes

The Seven Tribes have also been reported in today's Daily Telegraph. You can see the full details of the Electoral Calculus analysis here on our website.

You can also find out your own 3D political position, and that of your neighbourhood, by taking our short 3D survey.

Posted 20 April 2019