How did the local election predictions do? A first look
Welcome to the 212th edition of The Week in Polls (TWIP), a polling newsletter that always welcomes new readers. So please don’t keep TWIP secret; please share it with your friends and colleagues:
This time I take a first look at how the local election predictions performed in this week’s elections. I’ll return further to how the polls and seat models did, but for the moment, it’s a first look at how the council seat predictions performed.
This is followed by a summary of the latest national voting intention polls, seat projections from MRPs and the most recent party leader ratings.
Subscribers who pay for the full edition can also read ten insights from the latest polls and analyses, including:
Some good polling news for Keir Starmer;
What people think about the idea of Angela Rayner returning to the Cabinet; and
A misleading newspaper headline about the views of Muslims.
If you are not yet a paid subscriber, you can read all ten by starting a free trial now:
For more polling news as it comes in ahead of next week’s edition, you can also follow The Week in Polls on Bluesky.
My hopes were raised this week with the excellent news that Robert Caro has written 983 pages of his latest book about Lyndon B. Johnson.
And with that, on with the show.
How did the local election predictions do?
The final set of local election predictions (updated on the figures in last week’s edition) were:
The table is also online here and you may find that version easier to zoom in on. It’ll also be updated with any final minor revisions to the actual results figures.
One caveat to note about these numbers is that different predictors treated seats where there were by-elections or defections slightly differently, I think. E.g. if a seat was won four years ago by Conservatives but the person resigned and it was won by Labour in a by-election last year and then gained by Reform this time, is that a Reform gain from Labour or the Conservatives? But such issues do not add up to much variation in the overall numbers.
What can we conclude from this?
Here are the forecasters again, ranked by the root mean square error in their predictions (low is good, and the RMSE scores have been rounded off to the nearest whole number).
I’ve also included the chess champion or chess computer that I compared each to last week, though there were two predictions that came in after then and so escaped this labelling. I should also add that, given Kronaxis used synthetic data and Bombe didn’t, in some ways grouping them together is not especially helpful. Perhaps they are more a case of PC vs Mac…
Anyway, the numbers:
More in Common (79, Tigran Petrosian)
Politics UK (108)
Britain Votes Now (108)
PollCheck (140, Mikhail Botvinnik)
Robert Hayward (167, José Raúl Capablanca)
The Elections Centre (201, Mikhail Botvinnik)
Bombe (231, Deep Blue)
Britain Elects / New Statesman (314, Mikhail Botvinnik)
Sam Freedman (340, José Raúl Capablanca)
Stephen Fisher (452, Anatoly Karpov)
Kronaxis (570, Deep Blue)
Congratulations, Tigran Petrosian, sorry… More in Common.
UPDATE: As foreshadowed above, PollCheck did indeed use the state of the parties at the time of the election rather than the previous election results (i.e. taking into account defections and by-elections) as their baseline for their predictions. Based on that different baseline, their RMSE score is 68.
Several caveats need adding to that, in particular that several of those above also made other forms of predictions (e.g. on vote share and on council control) which I have not analysed. Plus there are the polls of the Welsh and Scottish elections and also the polls of vote share in various English local elections which are not included in the above.
For example, Kronaxis has shared with me some data on their vote share errors, which look to be coming in much better than their seat numbers did.
So there is plenty more analysis to come and plenty more rankings of performance too.
Tribal Politics: How Brexit Divided Britain
The latest episode of Never Mind The Bar Charts features the authors of a great new book, Tribal Politics: How Brexit Divided Britain.
Sara Hobolt and James Tilley discuss how the Brexit referendum was the trigger for new political identities, identities which have persisted.
We also discuss their surprising finding about the role for social media in forging anti-Brexit identities, as well as lessons from their research for pro-European campaigners.
You can take a listen via Spotify, Apple Podcasts, the web or in all the other usual podcast places.
Get the book
Tribal Politics: How Brexit Divided Britain by Sara Hobolt and James Tilley is available from Waterstones, Amazon and Bookshop.org (independent bookshops).
If you spot a factual error…
Borrowing an idea from Stuart Ritchie and others, if you spot a factual error in an edition of this newsletter, I will give you a free 12-month subscription to the paid-for version (or an extra 12 months on your existing one). Factual errors qualify; grammatical errors or disagreements over interpretation do not and my decision is final. Messages about both of those are always welcome, though.
Voting intention and leadership ratings
Here are the latest voting intention polls from different pollsters. Deltapoll is back with voting intention polling, and with a new methodology too.
The table is also online here, along with explanations about what is included. It is updated regularly through the week with new polls.
Next, the seat projections from MRPs and similar models, also sorted by fieldwork dates. Note that only two of these date from this year.
Finally, a summary of the latest leadership ratings, sorted by pollster name. Again, the previous negative trends for both Farage and Polanski persist in the data but we will have to see what this week’s results do to that.
The table is also online here with additional details and is updated regularly through the week as new data comes out.
For the historic figures on both voting intention and leader approval, including Parliamentary by-election polls, see PollBase.
Catch up on the previous two editions
My privacy policy and other legal information are available here. Links to purchase books or other items are usually affiliate links which pay a commission for each sale.
Quotes from social media messages are occasionally lightly edited for punctuation and clarity.
If you are subscribed to other email lists of mine, please note that unsubscribing from this one will not automatically remove you from the others. If you wish to be removed from all my lists, simply reply to this email to let me know.
Some good polling news for Keir Starmer, and 9 other polling insights you shouldn’t miss
The following 10 findings from the most recent polls and analysis are only for subscribers who pay for the full edition, but you can sign up for a free trial to read them straight away.
Approval ratings for Keir Starmer, whether compared with other party leaders, previous Prime Ministers or his own past, are consistently grim. But there continues to be one piece of polling good news he and his supporters can hang on to, and we saw that again in another recent poll.
