.@HerbieLewis There is a bigger question here: can you model very very rare events based on very very few cases, aka what 538 does?
-
-
Replying to @zeynep
.
@HerbieLewis The whole debate people are having is about 538 probability distributions; little debate on what those actually are.5 replies 0 retweets 7 likes -
Replying to @zeynep
I think the 538 "snake" of state outcomes is a great and informative. I'd personally chop off the top. Not as informative as people think.
3 replies 1 retweet 11 likes -
Replying to @zeynep
zeynep tufekci Retweeted Ben Lillie
Here's some good discussion. I don't think many people understand what the top of the 538 page actually represents.https://twitter.com/BenLillie/status/795455631423602688 …
zeynep tufekci added,
2 replies 2 retweets 8 likes -
Replying to @zeynep
zeynep tufekci Retweeted Andrew Perrin
Yep. Binary outcome=no way to judge the model. Poll avgs are plenty good info. No need to obsess over 538 topline.https://twitter.com/andrewjperrin/status/795457139229782016 …
zeynep tufekci added,
2 replies 1 retweet 7 likes -
Replying to @zeynep
So, there's other ways to validate overall model, right? EV projection, popular vote projection, 50 state outcomes/margins.
1 reply 0 retweets 1 like
I suspect where we'll find 538 is actually wrong is that the predicted winner wins more often than should happen by chance.
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.