Fraud pattern?
Polls in this election were (a) way off, and (b) almost always in the same direction. They underestimated support for Republican candidates by about 6 points on average. (Image via @SeanTrende.)pic.twitter.com/Qs8ZBzhuFG
-
-
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
just imagine what Trump would be doing if polls were off in the other direction.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Is that the “Latinx” vote?
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
This Tweet is unavailable.
-
Yes, of course. We're trying to estimate the attitudes of people who don't respond to polls from those of people who do. Not at all surprising there's a bias there, although we could wish it weren't so large.
- Show replies
-
-
-
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
But the errors are correlated, decreasing the surprise. The final result was well within 538's final electoral college projections.
-
No. That's a miss-read of the results. A ~300 win on a margin of 0.5% is not the same as that same ~300 on a margin of 5%. (An order of magnitude difference). Furthermore, if you look at the Congress and senate they are way off.
- Show replies
New conversation -
-
-
This Tweet is unavailable.
-
assumes trying
End of 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.