2012 was forecasted to be closer, split among forecasters; that communicates uncertainty, makes forecasting have less impact.
-
-
Replying to @zeynep
so most voters are checking multiple forecasters and factoring all of them into their decision making?
2 replies 0 retweets 0 likes -
Replying to @derekwillis
I think 538 and NYT upshot were key; they framed it everyone else, influenced a lot.
1 reply 0 retweets 1 like -
-
Replying to @derekwillis
Watching it unfold online and offline for a year, among many reporters who drove coverage, and many ordinary voters.
1 reply 0 retweets 2 likes -
Replying to @zeynep @derekwillis
I wish there was candid interviews with reporters right after election. They had not understood the uncertainty of forecasts.
3 replies 0 retweets 5 likes -
Replying to @zeynep
which reporters didn't understand that Trump was likely to win OH & that FL/NC were very tight? Which ones didn't see PA as key?
1 reply 0 retweets 0 likes -
Replying to @derekwillis
They didn't understand that, errors correlated means that a 1-2% shift changes the whole election. Different than 90% chance!
2 replies 0 retweets 2 likes -
Replying to @zeynep
Nate Silver literally talked about this all the time in last month. So is 538 influential or not?
1 reply 0 retweets 0 likes -
Replying to @derekwillis
He talked about it on Twitter; on footnotes; sometimes in long-form. Topline visual remained the same.
2 replies 0 retweets 2 likes
I complained about this before the election. Wanted a dial saying "Hey, errors are correlated. Move dial 1% see what happens."
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.