Agreed but you could see how it would give someone a bit of overconfidence
-
-
This Tweet is unavailable.
-
-
-
-
Which is entirely consistent with the observed outcome.
-
As is any probability < 1.
- Show replies
New conversation -
-
-
I get what you’re saying, but those probabilities(which were probably overconfident) were probably based on the consistency of the lead, not the size
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Probability and polling margin aren’t the same thing.
-
You're restating my point. This is what people (including journalists) saw when they opened the website of record.
- Show replies
New conversation -
-
-
This just in, a 15% probable outcome still has a 3/20 chance of happening.
-
After all, there is only a 14.28% of any give day being a Thursday, but they happen once a week!
End of conversation
New conversation -
-
-
Nate Silver was consistently more conservative in his probability estimates, so this is a problem with the NYT's analysis, not the polls.
-
Yes, the 0.02% of people who carefully read the text rather than looking at banner headlines got the correct information. Silver still bears responsibility for how that information was communicated on his site.pic.twitter.com/wvesy0buPp
- 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.