Nate Silver

@NateSilver538 ↗

Deleted No

Hibernated Yes

Last Checked April 26, 2020

Created

Wed Nov 27 01:59:15 +0000 2019

Likes

Retweets

Source

Twitter for Android

View Raw Data

JSON Data

View on Twitter

Likely Available

Nate Silver @NateSilver538

@gelliottmorris @DanRosenheck @mattyglesias I've gotten into this fight with folks before and the issue is that if you set a model that is deliberately conservative to reduce noise, you wind up in the uncanny valley where your polling aveage isn't quite predictive but also isn't quite descriptive of what polls say today. — PolitiTweet.org

Posted Nov. 27, 2019 Hibernated

Preceded By

Nate Silver @NateSilver538

Second, the effects are highly nonlinear. If you're stuck near 0-1% in national polls, being in your home state isn't going to get you very far. Maybe you'll get 3% or 5% or 10% instead of 1%. But it's not going to get you to 30% or something. You need to have a pulse nationally. — PolitiTweet.org

Posted Nov. 27, 2019 Hibernated

Followed By

Nate Silver @NateSilver538

@gelliottmorris @DanRosenheck @mattyglesias In other words, it's better IMO to have a polling aveage that captures the swings such as they are, and then revert toward whichever priors you like for making predictions, rather than have a slow-moving polling average. — PolitiTweet.org

Posted Nov. 27, 2019 Hibernated