Pages

COMBINED EU REFERENDUM FORECAST UPDATE

Our own blog posts and findings
----------------------------------
And then I found this on my travels, originally posted here
Last week we launched a combined forecast method, which we will endeavour to update weekly. There is very little change since the last forecast. The average probability that Remain will win has gone up 3 points because all individual forecasts now suggest a higher probability compared to last week, but there is almost no change in the average forecast share of the vote. All methods still show a strong consensus pointing towards a Remain win.
SHARE OF THE VOTEREMAINLEAVE
Betting markets54.945.1
Polls52.847.2
Expert forecasts56.243.8
Volunteer forecasts54.645.4
Poll based models55.644.4
Non-poll based models52.048.0
Combined forecast (mean)54.345.7
PROBABILITY THAT REMAIN WINS
Citizen forecasts66.6
Volunteer forecasts74.4
Prediction markets72.0
Betting markets67.2
Polls68.8
Poll based models76.4
Combined forecast (mean)69.8
Individual forecasts collected 26th April.
Details of methods and sources are below. The only change from the previous forecast is that the poll-based model from Number Cruncher Politics now provides a predicted share of the vote for Remain. We do not endorse any of the component forecasts. As mentioned below, there are a couple of prediction markets with very low trading activity that we have not used. Otherwise these are all the useable forecasts that we know about. We have not excluded any forecasts based on our judgement of quality. Please do let us know if there are any other published forecasts that you think we may have missed and could be using. More generally, the methodology is still under development so comments very welcome.
Citizen forecasting
Citizen forecasts come from the results of representative surveys of voters, asking them what they think the outcome will be. Such voter expectation surveys have an excellent track record, arguably better than polls, prediction markets, quantitative models or expert judgment for US presidential elections. The percentage who think that Remain will win is taken as a collective estimate for the probability of a Remain win. Results of voter expectation surveys are listed here. For each pollster we take the average of the last two such polls within the last three months, and then average across pollsters.
Expert forecasts
At the moment in this category we just have the results of the Times Red Box sweepstake podcast contributors as our experts, plus some others we can identify as experts.
We considered taking the proportion of experts who gave predicted Remain shares above 50% as a pseudo probability of a Remain vote. However this figure would have been 95% and not fairly represent the uncertainty felt by many of the expert contributors. Nonetheless this unity here is striking. Moreover, there are various other published expert forecasts but they are not used here because they do not provide figures for either the share of the vote or the probability of one side winning. They too overwhelmingly point to Remain winning.
We hope that there will be more systematic surveys of academics, pollsters and journalists in due course.
Volunteer forecasts
Philip Tetlock’s Good Judgement project encourages people to forecast the outcomes of various social and political events and helps them learn and improve their forecasting skills. Tetlock claimsthat given some training, effort and practice, reasonably intelligent citizens can forecast better than experts, at least collectively. One of their forecasting challenges is the outcome of the Brexit referendum (here).
In addition we use the volunteered contributions to the Times Red Box sweepstake, i.e. the participants excluding the podcast contributors. For some academics and others that we know of we have reclassified their forecasts as expert. The proportion of these volunteered contributions giving predicted Remain shares above 50% is again taken to be the probability of a Remain vote. The median Remain vote share is used for the share forecast.
Prediction markets
These are websites which allow people to bet on the outcome directly with other participants, without a bookmaker setting the odds (explanation here). They are much lauded as a forecasting tool by many economists and business people because they draw on views from a wide range of people willing to risk their own money. For election forecasting they arguably have a better track record than polls, quantitative models and expert judgement.
For the Brexit referendum the prediction market websites only have markets for which side will win not the share of the vote. We use data from predictit and hypermind. We also use spread-betting markets from sportingindex and ig, taking the mid-point of the spread as the predicted probability or vote share.
Because of low trading rates we do not use ipredict.
Betting markets
These are traditional bookmakers. Even though the odds are formally set by the bookmakers, with enough people betting they are primarily driven by what the punters are willing to accept. We average across major bookmakers listed here after correcting for the over-round (whereby the sum of the implied probabilities from the published odds is more than 100).
Bookies allow people to bet on the share of the vote within particular bands (e.g. 45-50% Remain). To generate a combined vote share forecast we take the mid-points of the bands and weight them by the (corrected) implied probabilities. For large bands that extend to 0 or 100 we do not use the mid-points but figures five points from the interior bound. For example, if the band is 75% to 100%, we use 80% for the share calculation. Implied probabilities for these extreme bands are very small so the choice of mid-point makes little difference to the calculations.
Polls
For the share of the vote we use the average of the polling averages that are published by whatukthinksBen StanleyNumber Cruncher Politicsthe FT, and ElectionsEtc. These polling averages typically aim to correct for differences between pollsters and so they should not fluctuate too much according to whether the most recent polls were online or telephone or from a particular company. So what we are calculating is a poll of polls of polls!
Since polling averages do not reflect the range of variance in the polls very well, we generate a pseudo probability for Remain winning from the proportion of polls that have Remain ahead. For this we take just the last two polls from each company-method combination within the last two months. So if a company has published two online polls and two phone polls in the last two months these are treated separately. Here we make no attempt to balance between online and telephone polls even though there are slightly fewer companies doing phone polls and they more clearly point more towards Remain.
Poll based forecasting models
Polls are a snap shot of opinion at the time they are taken. The historical relationship between polls and referendum outcomes tells us something about the direction and extent of any likely change in opinion, as well as the level of uncertainty we can expect of the outcome. Both ElectionsEtc.com and Number Cruncher Politicsprovide forecasts of this kind, now for both the probability of Remain winning and vote shares.
Non-poll based models
A traditional approach to election forecasting is to use historical data to develop a statistical model based on factors that are expected to influence the vote. These factors are often referred to as the “fundamentals”. See here for an introduction to these kinds of models for US elections.
The only such published model for the Brexit referendum that we know of is from Matt Qvortrup (see here and here). His latest estimate is here.

Survation for London Fairness Commission - New Mayoral Telephone Polling

With Polling Day fast approaching for London's Mayoral selection, Survation, on behalf of the London Fairness Commission are announcing results of new telephone polling of 1,010 London adults aged 18+ conducted between the 21st-25th April 2016.

Results indicated a clear desire for the next Mayor of London to make London a “fairer” city.
 
Key Findings.

Perceptions of unfair pay - Six out of 10 (59%) people told Survation that London-based organisations where lowest paid workers earn £13,500 (the minimum wage), that the fair, maximum salary for the Chief Executive should be not more than 20 times the lowest wage (£270,000).

Income Ratios - Similar in concept to the suggestions that have been made for addressing in-company gender pay inequality, two thirds of Londoners (66%) told Survation that companies employing more than 250 people should be required by law to publish the income ratio of the highest paid to the lowest paid worker in their organisations.

Should “Fairness” be Measured? - Three out of four people told Survation they believed the income gap between those on the highest incomes and those on the lowest incomes in London has increased over the last five years. The majority of people supported the idea of ‘London Fairness Index’ - an index that could to annually test whether London is a “fair” city - with one in five (22%) saying that it was ‘completely necessary’.

Who Owns London’s Property? - According to LFC’s research, over 36,000 properties in London are registered to offshore companies, meaning the identity of the ultimate owner is not publicly known; 76% of people asked believed offshore companies should be required to declare details of their property ownership in London.

The London Fairness Commission and London's Next Mayor - The London Fairness Commission’s recently published report underlined, in their view that London’s future success will be undermined if current problems are not resolved. The commission believes today’s polling demonstrates support of the Commission’s recommendations, which include:

  • Public disclosure of pay ratio data from companies and public sector bodies based in London

  • Ensuring companies registered offshore declare details of property ownership

  • That the future Mayor of London to be given powers of compulsory purchase on land/properties owned by offshore companies who are unwilling to declare the name of the ultimate beneficial owner

  • Ending so-called Land banking” by taxing land owners in London with planning permission for new homes who refuse to develop their land for longer than 3 years


Chair of the London Fairness Commission, Lord Victor Adebowale commented:
 
‘London’s future success is at risk if our city is not a ‘fair’ place to work, live and do business. While Londoners do earn more on average than the rest of the UK, the high cost of living, such as housing, transport and childcare, is making the city less fair. There is now a danger that London will become a playground for the super-rich, a treadmill for the middle-classes and a workhouse for the poor.

‘Unless the next Mayor of London takes the fairness of our city seriously, these issues will undermine the long-term success of the Capital. A London Fairness Index provides a way in which we can assess progress towards recovering the balance.’

Addionally, The London Fairness Commission believe their report is the first such work for 125 years - since Charles Booth mapped the levels of wealth and poverty across London in 1889, coining the phrase ‘the poverty line’ in the process - that a special commission has analysed the ‘fairness’ of London.

Chaired by the CEO of Turning Point and crossbencher Lord Victor Adebowale, The London Fairness Commission, c took evidence a wide range of Londoners including experts from business, academia, health and charity sectors over the past year, before reaching its conclusions.
  
The release of the Final Report was marked by an event at the Deck of the National Theatre which included a ‘job interview’ for  candidates for Mayor of London. So who might be London’s new Mayor?

As part of this telephone polling, Survation asked Londoners about their current first and second preference for London Mayoral candidate.

First Round – First Preference Mayoral Voting Intention

(Normal weightings, likelihood to vote, undecided and refused removed)
Sadiq Khan (Labour) – 49%
Zac Goldsmith (Conservative) – 34%
Peter Whittle (UKIP) – 5%
Caroline Pidgeon (Liberal Democrats) – 3%
Sian Berry (Green Party) – 3%
George Galloway (Respect) – 2%
Sophie Walker (WEP) – 1%
Paul Golding (Britain First) – 1%
Lee Harris (CISTA) – 1%
John Zylinski (Independent) – 1%
David Furness (BNP)  – <1%
Ankit Love (One Love Party)  – <1%

=> Second Round, after reallocation of first preferences 

(Normal weightings & likelihood to vote, removing those without at least one of CON/LAB in their 1st or 2nd preference)

Zac Goldsmith (Conservative) – 40%

Sadiq Khan (Labour) – 60%

Sadiq Khan – Was the candidate that some commentators opined ahead of his Labour Party selection (in which Sadiq won every part of the electoral college) would not have the ability if he became the candidate to secure even a narrow victory over Richmond MP Zac Goldsmith.  In today’s poll, Khan has almost enough first preference vote intentions to win City Hall back for Labour without needing a second round of voting if turnout for the Tooting MP holds up on polling day.
So is is all over for Conservative hopes of retaining City Hall for a third term?
To remedy this type of notional lead, and render these figures for the race for City Hall “inaccurate” by polling day, the Conservative Party campaign will have to perform what Lynton Crosby deemed in Boris vs Ken’s round one the “doughnut strategy” – differential turnout in Greater London’s “outer ring” except an even more extreme version – extremebeing a phrase oft bandied about during this campaign – to little apparent success.
However even throwing the “kitchen sink”  – a phrase used by David Cameron in the Rochester & Strood By-election at the Greater London electorate ahead of polling day to achieve the required turnout favouring the Conservative candidate is challenging and with polling figures heading in the opposite direction of Zac Goldsmith since last Autumn The Conservative candidates hopes of becoming London’s third Conservative mayor look distinctly unlikely.

A list of current sitting MPs who have lost the party whip

Source wiki

  • Michelle Thomson (SNP, Edinburgh West)
SNPIndependent: 29 September 2015
Thomson withdrew from the SNP whip after her business became the subject of a police investigation into alleged irregularities regarding property deals.[11] As a result, she now sits as an independent. In line with party rules, upon withdrawing from the whip, her SNP membership was suspended.
  • Natalie McGarry (SNP, Glasgow East)
SNPIndependent: 24 November 2015
McGarry withdrew from the SNP whip after being named as under investigation by the police regarding financial discrepancies relating to Women for Independence, a campaign organisation for which she is a founder.[12] As a result, she now sits as an independent. In line with party rules, upon withdrawing from the whip, her SNP membership was suspended.
  • Simon Danczuk (Labour, Rochdale)
LabourIndependent: 31 December 2015
Danczuk was suspended from the Labour Party, pending an investigation by the National Executive Committee, after allegations were made that he exchanged explicit messages with a 17-year-old girl. As a result of the suspension, he has been withdrawn from the Labour whip, and now sits as an independent.[13]

Latest Survation EU Referendum polling

In new polling on behalf of IG Group (Survation’s third EU Referendum telephone poll of 2016), "Remain" continues to lead; however, support for "Leave" has risen 2 per cent since our last poll on March 24th and four points since Survation’s initial telephone poll of the year on February 20th, after David Cameron’s EU Renegotiation announcement.

Survation interviewed 1,003 adults aged 18+ across the UK on behalf of IG Group by telephone from 25th-26th April 2016 on the question:

Imagine there was a referendum tomorrow with the question “Should the United Kingdom remain a member of the European Union or leave the European Union?” How would you vote?

Results are as follows with changes from the previous Survation poll (24/03) in brackets:
 

Remain 45% (-1); Leave 38% (+3); Undecided 17% (-2)
 

Excluding Undecided voters, headline results are:
 

Remain 55% (-2); Leave 45% (+2)


The “Undecideds”

Voters in the sample who initially told Survation they were undecided were then “squeezed” with the question:

“If the referendum was today and you had to choose, would you Vote for the UK to leave the European Union / Vote for the UK to remain a member of the European Union?”

Some of these undecided respondents then stated a preference for leave or remain after this “squeeze” question. Adding back these respondents to the initial voting intention has the effect of a slight (1%) boost to Remain:
 

Remain 56%; Leave 44%

Commenting on the poll findings, Damian Lyons Lowe, Chief Executive of Survation, who conducted the poll said:

“We’re very pleased to begin our partnership today with IG ahead of the EU Referendum, publishing regular polling results with a consistent methodology that will enable IG’s clients to observe public opinion trend from our work in February up until the week before polling day. 

As we saw in both the 2011 Alternative Vote and 2014 Scottish Independence Referendum, public opinion in such referendums has been subject to change from the effect of rival campaign activity, televised debates and other events that can swing public opinion. Survation’s series of polls for IG should be of interest for all those keen to consider what the UK will decide one way or another on June 23rd.”

Full data tables for this polling can be viewed
 here.


IG’s EU Referendum Barometer is still indicating victory for the Remain campaign, predicting a 73% chance that the UK remains within the European Union. The Barometer is an indicator of what those traders are predicting will happen in the 2016 UK referendum on membership of the European Union. The data is based on the political binary market IG has created for clients to trade on.

Matt Brief, Head of Dealing at IG said:

“The IG barometer is showing a 73% chance that the UK votes to remain in the EU. While the IG/Survation opinion poll is giving a snapshot of voting intentions from the last two days, our binary market (barometer) is a forward looking estimate of the likelihood of each side winning. IG clients have a history of predicting referendum and election results correctly such as the Scottish independence referendum, and at present they have REMAIN as strong favourite.”

A list of upcoming council by elections and vacant seats

Link also to >>> Council Election results June 2015 - April 2016

Collated by MiddleEnglander


There are currently 18 vacancies which will not be filled on 5th May together with 1 deferred election following the death of a candidate.

19th May - 1
Merton LB, St Helier - Labour died - 5 candidates: Con, Lab, LD, Green, UKIP

26th May - 2
Hambleton DC, Northallerton South - Conservative died
North Yorkshire CC, Northallerton - Conservative died

2nd June - 4
Argyll & Bute UA, Oban North & Lorn - SNP sitting as Independent resigned
Denbighshire UA, Diserth - Conservative died
Denbighshire UA, Lower Denbigh - Independent died
Dorset CC, Sherborne Rural - Conservative resigned

9th June - 1North East Lincolnshire UA, South - Labour resigned

Not yet called - 10Caerphilly UA, Gilfach - Labour resigned around 14th April
Cornwall UA, Newquay Treviglas - UKIP resigned on 8th April
Eden DC, Appleby (Appleby) - Independent died 20th April
Essex CC, Basildon Laindon Park & Fryerns - Labour died 7th April
Kings Lynn & West Norfolk BC, Valley Hill - Independent died 24th April 
Lambeth LB, Gypsy Hill - Labour died 23rd April
Luton UA, High Town - Labour resigned 11th April
Newark & Sherwood DC, Balderton South - Conservative died 13th March
Wiltshire UA, Trowbridge Grove - Independent died around 3rd April
Vale of Glamorgan UA, Rhoose - Independent killed in motor accident 31st March

Deferred Elections

2nd June -1
Rushmoor BC, Aldershot Park - Labour seat

Should Pairing for parliamentary votes be scrapped?

The Article by @IanDunt Originally posted here raises the question would governments be held more to account does pairing actually make it easier for the governing party?

--------

So I’ve come under a bit of flak for this piece, which suggests the refugee vote last night was lost because not enough Labour MPs turned up.

OK, so the piece is written in a style which is a little look-how-many-MPs-turn-up-to-debate-their-salary and probably I should have tuned that aspect down a bit. The headline was a misjudgement on my end. It is simplified to the point of unhelpfulness.
However, this isn’t just a mea culpa. A few people online are suggesting I’m playing down ‘pairing’ - an informal parliamentary procedure where MPs on both sides of a vote agree to balance out each other’s absence - in order to attack Labour.

Actually pairing is not quite as simple as all that. A party decides when it wishes to do pairing. It does not do so when the vote is very politically important.
For instance, Labour did not allow pairing on the votes over tuition fees or the bedroom tax. The fact that pairing is allowed for a vote demonstrates the relative importance attached to it by the party which does it. Given that this vote involved saving 3,000 child refugees from these conditions, that is a reasonable point to make.

It’s also argued that not allowing pairing just means you have to drag lots of sick or bereaved people into the Commons for a vote, or cancel a bunch of trips overseas. The argument runs like this: As an MP you inform the whips of your absence a few days before a vote. So ending pairing just means the Tories would have dragged their MPs back too.

That’s true, as far as it goes. But pairing is undeniable useful to the government. It means you can take a potential rebel in your own ranks and say: take the day off. No need to come in. Stay in your constituency. You can do that knowing that they will be paired and neutralised on the other side. It means you don’t need to keep your eyes on them on the day of the vote and prevents any opportunities for last-minute Damascene conversions. Basically, it makes life easier for the governing party.

I made a error not going into those details in that news story. I should have done it as a blog and teased them all apart. It was a quite significant error, because it threatens to mislead rather than inform the reader. That’s something we always try to avoid on this site.

But the use of pairing is not quite as simple as many people online make out. Labour were asked not to allow pairing on this vote by the Lib Dems. Would doing so have won the vote? It’s hard to say. Probably not. But Labour’s decision to allow pairing is worthy of mention on its own right, especially given the (rightly) high flying rhetoric coming from MPs on the Labours benches last night.