Oh, it’s very revealing about the overall mood of the electorate, along with who’s likely to actually vote any given year...
-
-
…it’s just not a statistically valid way to weight your results on horse race questions.
5 replies 0 retweets 0 likes -
an equal numbers. They ranged from somewhat heavy on Dems to more than 50% heavy on Dems.
1 reply 0 retweets 0 likes -
Replying to @SharylAttkisson @RayGuy3
Overall that’s consistent. Dems had about a 7% advantage on party ID last year. There's never been more self-identified Rs in recent years.
4 replies 0 retweets 0 likes -
Related question: what do you think of those percentages.. such as oing into election night, “538” showed Hillary w/ 71% chance winning
1 reply 0 retweets 0 likes -
Replying to @SharylAttkisson @RayGuy3
Based on that model, Trump had a 29% chance. That’s called an upset. Happens all the time in sports. I’m more skeptical of the models...
2 replies 0 retweets 0 likes -
…that claimed Trump had a <5% chance. That’s probably a sign of a bad model, considering where the polls were on election day.
1 reply 0 retweets 0 likes -
Does the model look at too many Democrats and not enough Republicans?
1 reply 0 retweets 1 like -
Replying to @SharylAttkisson @RayGuy3
Any model that looks at Ds vs Rs is probably a bad model,unless someone can come up with a model that predicts turnout based on affiliation.
1 reply 0 retweets 0 likes -
That said, I don’t believe any of the models tried to fit based on party ID. Rightly so. There are better ways to predict turnout.
3 replies 0 retweets 0 likes
Gotta go. Good talking to you and thanks
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.