Profile Image

Nate Silver

@NateSilver538 ↗

Deleted No
Hibernated Yes
Last Checked April 27, 2021

Created

Mon Aug 10 18:20:54 +0000 2020

Likes

223

Retweets

14

Source

Twitter Web App

View Raw Data

JSON Data

View on Twitter

Likely Available
Profile Image

Nate Silver @NateSilver538

But there are some important constraints here. Polls mostly have strong incentives to be accurate. And they are mostly run by people with a lot of experience (often a lifetime's worth) of doing polling. So an average reflects a consensus of expert judgement. — PolitiTweet.org

Nate Cohn @Nate_Cohn

I agree with the default assumption that diversity is good for averages, but this is taking it too far for me. Do w… https://t.co/8fsbA2jVsl

Posted Aug. 10, 2020 Hibernated

Preceded By

Profile Image

Nate Silver @NateSilver538

If I ran a poll, I'd definitely weight by education. But I'm not sure that a *polling average* made up of 100% polls that weight by education will be better than one where *most* polls weight by education, but some take alternative approaches. — PolitiTweet.org

Posted Aug. 10, 2020 Hibernated

Followed By

Profile Image

Nate Silver @NateSilver538

So if 20% of expert pollsters have thought carefully about these problems, and concluded education weighting causes more trouble than it's worth and there are better ways around the problem, I'm highly inclined to let them have their (still quite small) 20% weight in my average. — PolitiTweet.org

Posted Aug. 10, 2020 Hibernated