This is about to devolve into a horrible battle of Bayesians vs Frequentists. But let me get some popcorn...
-
-
-
my body is ready
End of conversation
New conversation -
-
-
Define validate.
-
I mean, how do you correct the model and say things like "it predicted a 45% chance of a Republican victory six months before the election, but in hindsight, it should have predicted 55%"
- Show replies
New conversation -
-
-
Disappointed that no one chimed in with an answer to this one. I'm not a statistician but am firmly in the camp "you can't validate probabilistic models of one-offs.”
-
I asked
@gelliottmorris about this before, but I think he's muted me or something - Show replies
New conversation -
-
-
Forecasting is worthless if the underlying drivers change...they always do. TV, real events, and $ and candidates change the underlying events in a heartbeat. Very useful to K Roves that can drive change and talking heads that pretend to understand math to drive 'narrative'.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
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.