It’s hard not to think, especially in light of the campaign messages over the last few days, that these hyper-“accurate”, exquisitely detailed models with no meaningful validation data might not be the best idea.https://twitter.com/MonaChalabi/status/1323819311400701953 …
-
-
ok, you win. :-)
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Yep, generally it's hard to have data to model rare events. And, polling is extra difficult when response rate is low and possibly, biased.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Also, public preferences != voter turnout
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
You are the smartest human alive I s2g
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
and everyone should spend more time outside and wear masks
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Would it be better to have pundits sound off on whatever quack theory about the electorate serves their own interests?
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
It’s modeling rare events that have ever changing inputs and hard to predict changes that is madness.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Being overconfident that you're correcting for biases when you have no clue what those original biases were, is probably the issue. Perhaps they also know that if they truly model it correctly the it will stay at 50-50 forever and no one wants to click that!
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.