You can add location information to your Tweets, such as your city or precise location, from the web and via third-party applications. You always have the option to delete your Tweet location history. Learn more
This article, written just before Trump's 2016 victory, is required reading for 2020https://www.google.com/amp/s/m.huffpost.com/us/entry/us_581ffe18e4b0334571e09e74/amp …
tldr; the author argues that a model that shows Clinton grabbing 265-340 electoral votes in 95% of simulated elections — and NO result <240 EVs — passes "the smell test" because it "produces plausible output" Quick refresher: Clinton wound up with 227 EVspic.twitter.com/VGZizRJIdS
I softened the blow a bit here — this author rallied his 20 years of experience in statistical model-building to question @NateSilver538's "professional competency" and "responsibility in reality checking" for *only* assigning Clinton ~2/3 odds of an electoral victory
I can't tell if he's just poorly informed about elections, or if he just doesn't get tail events on an intuitive level. 2.5 percentile events look weird! That doesn't mean they don't have a 2.5% chance of happening.
Yes, "event with 1% chance of happening seems very unlikely to happen, why are we assigning it any chance at all?" is a very head-desky take
2016 was Nate’s best performance in his career. Not only was he the only one to give Trump a chance, he also explained how he would win if he did (specifically, that there was no blue wall and that states like PA, MI, and WI were demographically similar and would move together)
And, for that, he was vilified before the election, and held responsible for everyone else’s bad forecasts afterwards. No narrative violations allowed.
The alarming thing isn't how wrong the author is -- it's that he will return to his job on wall street and continue to use the same flawed methodology to create financial models. Others will do the same in other fields, acadamia, etc.
The polls in 2016 essentially failed. PPL who voted for Trump either refused to cooperate w/ pollsters, or had so much embarrassment over their decision to vote Trump, that they refused to answer truthfully or participate at all in polls. But we have secret ballots. 2020 same.
Except that national polls basically nailed the outcome. And error of about 1 point. They were much closer to the mark than they were in 2012. State polls in the Midwest were off the mark but not wildly so.
You keep using that word, I do not think it means what you think it meanspic.twitter.com/R1TPzijw7y
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.
