Um, poll Twitter. State errors may be correlated. More interesting Q: can we model a rare event based only on 11 previous cases—as 538 does?
-
-
They can at least place upper bounds on the prob of rare events with few inputs, no? Albeit not very low upper bounds.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
I think the 538 "snake" of state outcomes is a great and informative. I'd personally chop off the top. Not as informative as people think.
-
I'd question the whole statistical approach. NYT: "Trump's chances equivalent to 38-yard-FG being missed". It's just daft.
End of conversation
New conversation -
-
-
Before UK election last year, respected models stated 0% probability of a Conservative majority. Which then happened.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
I think Silver's been spooked by polling failures and has built too much conservatism into the model
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Some of these statements seem problematically inconcrete. "Little debate about what those are" What does this mean?
-
Huge debate on 538 topline; little discussion on meaning of modeling a rare event with binary outcome via simulations.
- Show replies
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.