Nate Silver

Nate Silver @NateSilver538

Something else worth mentioning—it's common sense but it shows up in the data—is that you should be mildly distrustful of pollsters without a track record. As a rule of thumb, it takes about 20 polls before you can have much confidence that what pollster does is working. https://t.co/xdRRsUEZOa — PolitiTweet.org

Nate Silver @NateSilver538

That doesn't mean that quality doesn't matter. We find that pollsters that participate in professional transparency/data-sharing initiatives continue to get considerably better results. The pollster ratings will continue to reflect this. https://t.co/gsp1olV914 — PolitiTweet.org

Nate Silver @NateSilver538

For another thing, it no longer really makes sense to classify entire *polling firms* by their methodology. Lots of polling firms mix-and-match methodologies, change them in midstream, etc. Methodology is a characteristic of a poll, not the pollster. — PolitiTweet.org

Nate Silver @NateSilver538

The other big finding is that we no longer see a clear rationale to give live-caller polls a higher grade by default in our pollster ratings. For one thing, they haven't particularly outperformed other methodologies. https://t.co/iy502D79RU — PolitiTweet.org

Nate Silver @NateSilver538

In an environment where politics are highly nationalized and polarized, you don't really have "50 separate contests" for the presidency. For that matter, presidential and downballot outcomes are highly correlated. So if your polls are off in one race, they may be off everywhere. — PolitiTweet.org

Nate Silver @NateSilver538

don't think we should necessarily expect that polls will continue to have a anti-Republican bias. Historically, the direction of bias is not very predicable as pollsters adjust, adapt, etc. But I do think we may continue to see systematic polling errors in BOTH directions. https://t.co/qRvINCmkLN — PolitiTweet.org

Nate Silver @NateSilver538

I don't think we should necessarily expect that polls will continue to have a Republican bias. Historically, the direction of bias is not very predicable as pollsters adjust, adapt, etc. But I do think we may continue to see systematic polling errors in BOTH directions. https://t.co/HNDlpmHqb8 — PolitiTweet.org

Nate Silver @NateSilver538

That's the biggest bias in either direction in the cycles our pollster ratings cover (since 1998). It's likely that some earlier years, certainly 1980 and probably 1994, would have had a bigger bias if you extended back that far. So not unprecedented. But still ... not ... good. — PolitiTweet.org

Nate Silver @NateSilver538

But here's the problem that's much harder to excuse. The polls had a big Democratic bias (bias meant in a statistical sense). Republicans beat their polls by 4.8 points on average! The bias was actually larger in Congressional & gubernatorial races than for Trump (4.2 points). https://t.co/tKRhN5TDLM — PolitiTweet.org

Nate Silver @NateSilver538

Is that the best way to evaluate polls? No. It's better to look at the margins. The D wins came by far closer margins than polls projected. Still, the media tends to judge polls by winners and losers so the 💩 the polls got was a tad inconsistent with how they're often evaluated. — PolitiTweet.org

Nate Silver @NateSilver538

The polls actually did pretty well in "calling" races correctly, as 79% of polls identified the right winner, which is the same as the historical average. Polls got 48 of 50 presidential states right, correctly identified that Democrats would win Congress, etc. https://t.co/C7vHo8Klvj — PolitiTweet.org

Nate Silver @NateSilver538

Based on average error, the 2019-20 cycle featured decidedly mediocre polling: an average error of 6.3 points. That's the 3rd worst out of 12 cycles we've tracked. At the same time, as you can see, it's not an outlier exactly, either. It was well within the range of "normal". https://t.co/qZmcBwTP9g — PolitiTweet.org

Nate Silver @NateSilver538

The next key link is to my feature article, "The Death of Polling is Greatly Exaggerated", which argues that the death of polling is greatly exaggerated. https://t.co/kfr7ND5OTN — PolitiTweet.org

Nate Silver @NateSilver538

Or if you want to go even deeper, you can find the entire database on GitHub. We strongly encourage people to use this database for academic research, etc. A LOT of hours of gone into building and maintaining it. https://t.co/SklfGhDACo — PolitiTweet.org

Nate Silver @NateSilver538

Note that we now have pages for individual pollsters. So you can see exactly which polls made it into the rating for each polling firm. Basically this means every poll within 3 weeks of an election since 1998! https://t.co/gjZSokHTdX https://t.co/rapX7CQa3E — PolitiTweet.org

Nate Silver @NateSilver538

Our new pollster ratings are up! They've been updated to reflect the results of the 2020 general election + the GA runoffs. Also a shiny new interactive. Fivey Fox makes a cameo appearance. Here's the link. I'll discuss some key findings in this 🧵. https://t.co/HBex5M5zFm https://t.co/JJiJDxOXpF — PolitiTweet.org

Nate Silver @NateSilver538

@notdred Yeah, that's one way to put it. I'm not persuaded by ZeroCOVID at least for large countries like the US. But I think you can make an honest, intellectually coherent case for it. It also has some advocates who get into some pretty bad fearmongering though. — PolitiTweet.org

Nate Silver @NateSilver538

Making a note to myself to check up on these in a few weeks but these projections strike me as pretty darn pessimistic in a world where vaccination rates are rapidly increasing. — PolitiTweet.org

Nate Silver @NateSilver538

Bonus tweet: Nice plunge in positive test rates for people aged 75+ in NYC, who were the first to be vaccinated. https://t.co/qWfBOTS37e — PolitiTweet.org

Nate Silver @NateSilver538

Update: NYC finally updated its COVID data and it agrees with the state, more or less. Clear signs of a plateau in cases and the positive test %. Hospitalizations still declining (though ignore the grey part of the chart, which has incomplete reporting). https://t.co/FzTtPAVIGR https://t.co/14HJ4oFwGM — PolitiTweet.org

Nate Silver @NateSilver538

RT @ashishkjha: @NateSilver538 @conor64 Yes! Active volcano pandemic safety rules: >50 feet distance masks unhelpful (will get covered… — PolitiTweet.org

Nate Silver @NateSilver538

@ashishkjha @conor64 Now you've made the guidelines impossibly hard to follow. There's an *entirely different* set of rules in the presence of an *active volcano spewing molten lava*? — PolitiTweet.org

Nate Silver @NateSilver538

@conor64 Seems like you're glossing over the real issue: the lack of proper #SocialDistancing. — PolitiTweet.org

Nate Silver @NateSilver538

@ZoeMcLaren One thing that I hope the profs will consider is that if a student claims to be at less than 100% for a day or two after their shots, they're probably not BS'ing! That's what the clinical trial data shows (and I've seen lots of IRL examples from friends, etc. too). — PolitiTweet.org

Nate Silver @NateSilver538

I keep writing "polling firms" in an article I'm working on and my editors keep changing it to "pollsters" and it's showing up as "pollstering firms" in track changes mode and that's what I'm going to call them from now on. — PolitiTweet.org

Nate Silver @NateSilver538

Source material here. https://t.co/JrUEWWBRCQ — PolitiTweet.org

Nate Silver @NateSilver538

Boroughwise, here is the current 7-day average case counts as compared to 3 weeks ago: Borough: Now / 3 weeks ago Queens: 1180 / 1093 Brooklyn: 1184 / 1228 Bronx: 645 / 794 Manhattan: 612 / 629 S.I.: 301 / 255 — PolitiTweet.org

Nate Silver @NateSilver538

NYC/NYS have reasonably high per-capita rates of COVID cases, but you need to adjust for testing volumes when comparing across states. Per capita, NYS is doing ~2.5 more tests per capita than the US overall, so we're capturing more of our infections than most states do. — PolitiTweet.org

Nate Silver @NateSilver538

On the other hand, I'm seeing a lot of loose talk about a "spike" in NYC when, no, that isn't really justified either. For better or worse, the numbers have settled into a plateau, which is also the case throughout the Northeast. https://t.co/k6mkUUTrTc https://t.co/Nfx7TvGEY4 — PolitiTweet.org

Nate Silver @NateSilver538

On the one hand, I'm pretty sure that sites showing a decline in NYC (the NYT shows this, for example) are wrong. They're filling in missing city data with state data for the city. But that state data isn't apples-to-apples; it doesn't include probably cases, for instance. — PolitiTweet.org