Nate silver was more right about the results than any other stats guy thoughhttps://twitter.com/RenderuntoG/status/1047868088429903873 …
-
-
Nate was right in that he emphasized that polling errors in midwestern states would he correlated, ie if one was wrong they were probably all wrong
-
Not a high bar, but he was the only guy who incorporated that into his predictions rly
-
I mean it was too difficult for the Clinton campaign to understand
End of conversation
New conversation -
-
-
you could easily get it right by aggregating data, *even w/o polls*; problem is polls are built around assumptions about turn-out, non-response etc, and these were all v bad
-
There are so few solidly blue districts left we could probably also figure out the Ballot Stuffing Advantage too.
-
lol, i actually doubt that is possible b/c left also has Full Spectrum Media Advantage - hard to disentangle two
End of conversation
New conversation -
-
-
If I remember right alt hype took primary data for trump and worked out some algorithm that came close during the general. He did some work to factor in people who weren’t polled
- 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.