United Kingdom General Election: July 4, 2024

[Florida Man for Crime]

Why are there so many MRPs this election?

And especially multiples from the same outfit. Maybe the calculation times are less? I’m guessing there’s some sort of Bayesian framework behind these and that can take a while to run.

In general they should be using some form of markov chain monte carlo, which is definitely computationally intensive.

However, you can buy basically unlimited computing time/power on cloud computing services (Amazon for example) to run things a lot more quickly. So the biggest time/cost obstacles are getting a large enough number of respondents for the large sample sizes required.

Basically it is simulating random collisions of particles like in particle physics as a method of optimization to find the most likely [maximum] values for things given the data in the sample.

(gif of particle banging randomly around on a gradient map, the places where it most often goes on average in the multi-dimensional space are the places which are statistically most likely, so basically the area of statistical uncertainty is mapped out by the density of the green color):



https://en.wikipedia.org/wiki/Hamiltonian_Monte_Carlo

https://mc-stan.org/docs/2_33/stan-users-guide/coding-mrp-in-stan.html

[Filuwaúrdjan]

I would suggest simply ignoring Professor Badwin and his 'polls'. He is not a credible or good faith actor and neither is anything that he does. He is a partisan agitator at best.

[JimJamUK]

https://twitter.com/Survation/status/1803438162468807155
Looks like Farage is heading to Parliament

Paid for by Arron Banks (pro-Farage businessman), and oddly over a 5% increase in his lead since a January poll which already had him winning by 10%.

[Joe Republic]

MRPs being very much the in thing, there's another one from More in Common:

https://twitter.com/LukeTryl/status/1803442656955244861

Those seat projections are remarkably similar to the 1997 result.  Which at this point seems to be the Tories' best case scenario..?

[JimJamUK]

The crosstabs of this poll are massively entertaining… Labour at 20% in Scotland, 17 points adrift of the SNP, whilst simultaneously being in a statistical tie with Reform in the Midlands and Wales.

At least they’re not accidentally on 0% again…

[Filuwaúrdjan]

I'll go a little further, and if this has to be deleted or edited I don't particularly care. The man is a fraud and so are his works and this is a pathetically obvious attempt at narrative manipulation in order to bolster the political party that he presently supports.

[Torrain]

The crosstabs of this poll are massively entertaining… Labour at 20% in Scotland, 17 points adrift of the SNP, whilst simultaneously being in a statistical tie with Reform in the Midlands and Wales.

At least they’re not accidentally on 0% again…

Honestly, there's a part of me that wonders if they've just screwed up their Excel tables again. Would be far more plausible than the final headline result.

[🦀🎂🦀🎂]

Honestly given the improvement to constituency polling, I wish the money was flowing to them instead of these dubious MRPs. There are a lot of seats where we have no clarity at all (not just headline grabbers like Clacton and Richmond, but the various seats where three or more different parties could feasibly be in competition). Because frankly some of the individual results in the MRPs are stinking piles of crap.

[Torrain]

Honestly given the improvement to constituency polling, I wish the money was flowing to them instead of these dubious MRPs. There are a lot of seats where we have no clarity at all (not just headline grabbers like Clacton and Richmond, but the various seats where three or more different parties could feasibly be in competition). Because honestly some of the individual results in the MRPs are stinking piles of crap.

100% - I'd take a single East Ren or Dumfries & Galloway poll over another five MRPs.

[oldtimer]

Honestly given the improvement to constituency polling, I wish the money was flowing to them instead of these dubious MRPs. There are a lot of seats where we have no clarity at all (not just headline grabbers like Clacton and Richmond, but the various seats where three or more different parties could feasibly be in competition). Because honestly some of the individual results in the MRPs are stinking piles of crap.

Are you sure that Constituency polling is the way ? :

https://www.wrexham.com/news/local-straw-poll-mirrors-uk-national-predictions-with-not-much-enthusiasm-over-general-election-253105.html

Their 2019 one for comparison:

https://www.wrexham.com/news/wrexham-straw-poll-results-with-just-two-weeks-to-until-the-general-election-177370.html

[GenerationTerrorist]

Having booked 5th July off work as soon as the Election Date rumours started, I intend to entertain you all night long!

[JimJamUK]

I’m pulling an all-nighter but I don’t have the Friday off. Wish me luck 😎

[The Mikado]

MRPs being very much the in thing, there's another one from More in Common:

https://twitter.com/LukeTryl/status/1803442656955244861

The funny thing is if you asked the Tories whether they'd lock this in or gamble on playing out the rest of the election I think they'd take it in a heartbeat. This is a pretty good night for them at this point and that's deeply telling.

[Spectator]

The GOP in the US probably needs a crushing defeat like this for it to finally renew as a serious major party. Trump’s loss in 2020 wasn’t decisive enough, so here we are. Death by a thousand paper cuts as Trump has been the face of the party among those that came of age and started voting in the past decade. Millennials and Gen Z are lost. The Xers and Boomers can only carry us for so long.

[oldtimer]

The GOP in the US probably needs a crushing defeat like this for it to finally renew as a serious major party. Trump’s loss in 2020 wasn’t decisive enough, so here we are. Death by a thousand paper cuts as Trump has been the face of the party among those that came of age and started voting in the past decade. Millennials and Gen Z are lost. The Xers and Boomers can only carry us for so long.

I think the closest analogy of what's going on with the British Conservatives would be if the GOP ditched Trump for Haley, resulting in a 3rd party overtaking them.

The polls already showed Haley coming 3rd in that scenario, so there's backup.

[TiltsAreUnderrated]

I’m pulling an all-nighter but I don’t have the Friday off. Wish me luck 😎

Same (probably).

[Torrain]

https://twitter.com/RachaelBurford/status/1803524360143249877

[TheTide]

The GOP in the US probably needs a crushing defeat like this for it to finally renew as a serious major party. Trump’s loss in 2020 wasn’t decisive enough, so here we are. Death by a thousand paper cuts as Trump has been the face of the party among those that came of age and started voting in the past decade. Millennials and Gen Z are lost. The Xers and Boomers can only carry us for so long.

All we needed was a US-centric post. Also, anyone who thinks that large groups of voters (categorised by nothing other than the twenty year period in which their parents happened to f**k) are a lost cause really shouldn't be playing the political game.

[brucejoel99]

Why are there so many MRPs this election?

https://twitter.com/markmcgeoghegan/status/1803419846702485920

[Pres Mike]

The GOP in the US probably needs a crushing defeat like this for it to finally renew as a serious major party. Trump’s loss in 2020 wasn’t decisive enough, so here we are. Death by a thousand paper cuts as Trump has been the face of the party among those that came of age and started voting in the past decade. Millennials and Gen Z are lost. The Xers and Boomers can only carry us for so long.

I think the closest analogy of what's going on with the British Conservatives would be if the GOP ditched Trump for Haley, resulting in a 3rd party overtaking them.

The polls already showed Haley coming 3rd in that scenario, so there's backup.

Both Rishi and Haley are second generation Indians and both come from the more tradational wings of the Conservatives/Republicans

[Sestak]

https://twitter.com/politlcsuk/status/1803542917111488709?s=46

[Sorenroy]

This ended up being a much larger task than I had initially expected, but given we had three MRPs released today, I decided to go through and see what the commonalities were between the three models. Party colors are from Wikipedia's Colors Guide with seats where all three MRPs agreed on the leading party a third darker. That means that even if all three MRPs showed a 1% lead, if that lead was consistently for the same party, the darker color is shown.



Yet Another Political Map Simulator Link
Labour — 440 (387+53)
Conservative — 109 (32+77)
Liberal Democrats — 59 (36+23)
SNP — 12 (7+5)
Plaid Cymru — 4 (2+2)
Green — 1 (0+1)
Unclear — 6

Party — MRP Average (All Three Models+Two Models)

More in Common's MRP
Savanta's MRP
Yougov's MRP


Some interesting notes: because each model was done independently and modeling at the individual constituency-scale can often result in weird numbers, even the worst individual projection for each party will contain won seats the other MRPs do not. For example, More in Common modeled Labour winning 406 constituencies, yet only agreed with both other models on 387 of them. On the other end, Savanta modeled the Conservatives ahead in 53, but only agreed upon 32 individual seats. Perhaps the largest impact of this was for the Scottish National Party, where even though Yougov found them ahead in 20 seats (maintaining more of their seats around Scotland's cities) and More in Common Found them ahead in 18 (maintaining more of their seats in the far north), the overlaps of agreement only had 12 seats where at least two of the three models showed holds.

The six unclear seats are seats where all three models showed different results. Four of them - Basildon and Billericay, Clacton, Great Yarmouth, and Louth and Horncastle - were seats where More in Common found the Conservatives leading, Savanta showed a lead for Labour, and YouGov showed a lead for Reform (the only model to show any Reform wins). The other two are Chichester and St Neots and Mid Cambridgeshire, where More in Common found the Conservatives leading, Savanta showed a lead for Labour, and YougGov showed a lead for the Liberal Democrats.

There is a lot of other interesting stuff about the individual MRPs, but the biggest standout to me was the implied vote share shown by More in Common. Their modeling on the Conservative performance is completely different from the other two despite having the exact same vote percentage for Labour as Savanta and having at most only a two point difference on the Liberal Democrats' numbers from both other models. The difference is the Conservative/Reform split. More in Common shows the implied percentage for Conservatives at 28%, seven percent higher than current polling and at least five points higher than either of the other models. On the other hand, they show Reform at only 8%, seven percent lower than current polling (Nearly half of their support!) and at least five points lower than either of the other models. That massive difference is almost the entirety of the difference between their modeled outcome and Savantas, as Labours best and worst model today show them with the exact same implied percent of the vote.

[Steve from Lambeth]

i notice it also shows reform second in Truss's seat nearby

Did Ipsos ignore Bagge, the Independent Conservative, in their polling? Why do professional MRP polls fall into the same "every race in each nation is being contested by essentially the same parties"/"Labour wins Islington North by a huge margin" trap that everymen tinkering with Electoral Calculus and PrincipalFish do? At this rate, we might as well have OnePoll the world-famous novelty pollsters doing the MRPs; they're trusted by everyone from the Walt Disney Corporation to, erm, Equals Money.

This is absolutely disgraceful. It is also obviously rather stupid for other reasons and, I suppose, interesting for the level of panic implied.

Why was the first person to discuss this leaflet on anything approaching a noteworthy scale that guy from British Future rather than an actual Dudley constituent? (My apologies if the British Future guy lives in Dudley, though.) This reminds me more than anything of that one time last year when H&M in Australia were successfully accused by the (UK citizen, UK resident) founder of Mumsnet of putting out an advert that sexualised young children, without any major intervention from any Australians.

Also, Kashmir is a totemic issue for some - although far from all - Indians and Pakistanis in the Labour movement (the debate within the Conservative Party is close to non-existent), enough so that the Corbyn-era manifestos included a paragraph emphasising Labour's hope for a peaceful resolution to that dispute. It is universally considered not to be a political issue that will ever lend itself to dignity and, as memory serves, all past attempts to drag it out into the open during election campaigns have met with a similar reaction in principle (although not to the extent shown here).

[Harlow]

https://twitter.com/politlcsuk/status/1803542917111488709?s=46

https://twitter.com/JAHeale/status/1803489495834067420

[OSR stands with Israel]

The GOP in the US probably needs a crushing defeat like this for it to finally renew as a serious major party. Trump’s loss in 2020 wasn’t decisive enough, so here we are. Death by a thousand paper cuts as Trump has been the face of the party among those that came of age and started voting in the past decade. Millennials and Gen Z are lost. The Xers and Boomers can only carry us for so long.

The Tories arent gonna renew themselves as a serious major party for at least a decade after this