I think UNS is fine for small changes in share. It's hopeless for large changes and clumping effects. I have an additive model (UNS) and a multiplicative model. If LibDem national share goes fro… (View Post)

There are a lot of true blue sensible middle of the road Tories who feel the same way. (View Post)

Bristol Greens might be a special local case. My model doesn't warrant decimal point accuracy! (View Post)

Great. Many thanks. What a resource! (View Post)

OK @Philip_Thompson I've picked the first in your list - Bristol North West. 2017 Con 22,639 Lab 27,400 Valid voters 54,096 Con share 40.1% ie. -3.4% of 2017, or 92% of 2017 Lab share 30.2% (inc… (View Post)