Owen Winter
Political data journalist at The Economist
- Estimating pollster house effects for a Hungarian poll tracker. Quite revealing!
- [Not loaded yet]
- The names on the left are polling firms in Hungary. Government-aligned firms tend to skew towards higher numbers for Fidesz in their polls
- The Hungarian Socialist Party might not run in 2026, for the first time since democratisation hvg.hu/itthon/20260... The party was in power for 12 of the first 20 years of post-communist Hungarian democracy
- [Not loaded yet]
- I guess in theory it makes it more likely that DK gets over the threshold but in practice MSZP were already polling at ~0% so not sure it makes much difference
- MSZP-ification
- For UK comparison: Liverpool 40% Manchester 39% Nottingham 38% Brighton/Hove 37% Newcastle 37% Hull 35% Cambridge 34%
- [Not loaded yet]
- yep!
- [Not loaded yet]
- Here! www.ons.gov.uk/datasets/TS0... or in a nice interactive map here www.ons.gov.uk/census/maps/...
- [Not loaded yet]
- 42%
- Yglesias conceptualize the idea of uncertainty: challenge rating --- impossible
-
View full threadMatt is mistaking a 1.5-2 _AME_ for the uncertainty in the response/misattributing the estimate to B/G instead of Elliott (+conjecture, I think he's also mistaking the 1.5-2 AME for voteshare, rather than margin). We can/should be honest about forecast uncertainty based on a dataset of <20 cycles
- Strongly agree re: forecasts and the conclusions in the screenshot, I'm just not sure what P(50) -> P(55) adds. Is that not just another stat which is uncertain to the point of being meaningless because models can't capture election dynamics?