For UK folks on the YouGov "MRP poll":
In 2017, YouGov did well because their poll had the *overall topline vote* about right, showing only a narrow Tory margin. Their MRP model did NOT do a particularly good job of translating votes into seats, however.
yougov.co.uk/topics/politic…
In 2017, YouGov did well because their poll had the *overall topline vote* about right, showing only a narrow Tory margin. Their MRP model did NOT do a particularly good job of translating votes into seats, however.
yougov.co.uk/topics/politic…
Many other pollsters had the Tories winning big. So YouGov deserves much credit for getting the topline number roughly right.
The MRP/model part itself (translating votes->seats) was meh though. If YouGov had Tories up 10 like other polls, their seat # would have been way off.
The MRP/model part itself (translating votes->seats) was meh though. If YouGov had Tories up 10 like other polls, their seat # would have been way off.
So the news in YouGov's poll tonight is that it has Tories up 11 UK (fairly typical of recent polls). It's no surprise that Tories would expect to win lots of seats if that's the final margin. But MRP is not magic. It's an OK/reasonable technique but its powers are overstated.
