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?
Some. Not enough to make or judge predictions to tenths of a percent.
-
-
tenths of percent are obviously meaningless, Andrew Gelman complained about it today http://andrewgelman.com/2016/11/06/different-election-forecasts-not-different/ …
-
Does anyone (538 included) claim the errors are on the scale of 1/10ths of a percent? I don't think so
- Show replies
New conversation -
-
-
But they don't really. They don't say the margin of error is tenths of a percent.
-
This says almost all i wanted to say, longer than 140. http://andrewgelman.com/2016/11/06/different-election-forecasts-not-different/ …
End of conversation
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.