Share this page!

Ariel Edwards-Levy Profile picture
Twitter logo
18 Mar, 5 tweets, 2 min read
This is one thing that'll be really interesting to keep an eye on. I've thought for a while that if there's a social-trust driven non-response issue with election polls, that same bloc of non-responders would be likely to inflate vaccine numbers by a few points.
Will obviously be useful to have more comparison points - FWIW, when I looked at this a few weeks back when I was doing coronavirus polls for HuffPost/YouGov, our national numbers were tracking pretty well with national vaccination rates, although not sure how it's evolved since.
Further thought...if overestimating vaccination rates ends up being especially prevalent either in certain states, or in polls with particular modes/sample frames, that will also be fascinating data. (And again, way too early to start hypothesizing yet, but something to watch.)

• • •

Missing some Tweet in this thread? You can try to force a refresh
　

Keep Current with Ariel Edwards-Levy

Ariel Edwards-Levy Profile picture

Stay in touch and get notified when new unrolls are available from this author!

Read all threads

This Thread may be Removed Anytime!

PDF

Twitter may remove this content at anytime! Save it as PDF for later use!

Try unrolling a thread yourself!

how to unroll video
  1. Follow @ThreadReaderApp to mention us!

  2. From a Twitter thread mention us with a keyword "unroll"
@threadreaderapp unroll

Practice here first or read more on our help page!

More from @aedwardslevy

Ariel Edwards-Levy Profile picture
21 Mar
Partisan split is an easy takeaway here, but the way that *everyone* is overestimating (half of GOP/60% of inds are in top two categories!) I think lends itself to a bigger point about the difficulty of estimating probabilities, and translating small %s into so many lives.
Also, people (myself often included) are phenomenally bad at estimating percentages in general. I actually wonder whether people would have done better generally if instead of the numbers they got a more subjective/intuitive scale (e.g. "most," "about half," etc.)
Quite possibly not! But would be an interesting experimental design...
Read 5 tweets
Ariel Edwards-Levy Profile picture
18 Mar
What Can We Polarize Next, the game show
To put into context, that's a significantly wider gap than on vaccine refusal.
These rapid cultural polarizations (see also: Kanye, the NFL, etc.) are always fascinating to me, because they seem silly, but also makes sense — presumably many Americans' partisan sentiments are stronger than their previous opinions on, say the royal family.
Read 4 tweets
Ariel Edwards-Levy Profile picture
11 Mar
Also want to briefly highlight a poll finding I wasn't able to write up, but that I think might be useful for discussion!

There's been a lot of debate over public health messaging on the benefits of the vaccine, which raises the question: what do people think that message is?
We asked people what level of risk they thought they/others would face once vaccinated -- as you can see, clear education/partisan divides. Field dates are Feb. 19-23:
s.crunch.io/widget/index.h…
s.crunch.io/widget/index.h…
57% of people thought scientists were saying being vaccinated put them at lower (52%) or no (5%) risk of coronavirus. 11% said no decline in risk, rest were unsure or said science not yet settled.
Read 5 tweets
Ariel Edwards-Levy Profile picture
11 Mar
Hi all -- just wanted to pop in quickly and say thank you for all the kind words and support, which are beyond deeply appreciated during a somewhat overwhelming week.
I also just want to take a moment to reflect on the HuffPost/YouGov poll. In my time running the partnership since 2014, we've fielded more than 1,000(!) surveys, asking Americans about everything from economic hardships and gun violence to the correct pronunciation of "GIF."
We've rerun historical polls from the 1930s to see what's changed, and checked into to see how people coped.

Not one of those polls included the question "Which candidate will you vote for?"
Read 8 tweets
Ariel Edwards-Levy Profile picture
13 Jan
One thing that's probably worth mentioning as impeachment polling starts to come out: Until we have a better sense of factors behind 2020 election polling error, can't discount that some of the same factors are affecting non-election political surveys.
To the extent there was a likely-voter-model problem, that's not a factor. But differential non-response very well could be.

Reasonable hypothesis that national impeachment polling might understate opposition by up to 3-4 points.
Compared to elections (where slim margins can be crucial), something like 39% opposition vs. 42% opposition isn't as meaningfully different.

But it's probably a good reminder that all these numbers are, by definition, estimates.
Read 6 tweets
Ariel Edwards-Levy Profile picture
13 Jan
in most other presidencies we do not impeach even once

why, in this presidency, do we impeach twice
(because twitter is bad at rhetorical questions, I feel like I need to stipulate ahead of time that this is a riff on the Four Questions)
with regret, I inform you that people are not reading the stipulation
Read 5 tweets

Did Thread Reader help you today?

Support us! We are indie developers!

This site is made by just two indie developers on a laptop doing marketing, support and development! Read more about the story.

Become a Premium Member ($3/month or $30/year) and get exclusive features!

Become Premium

Too expensive? Make a small donation by buying us coffee ($5) or help with server cost ($10)

Donate via Paypal Become our Patreon

Thank you for your support!

Follow Us on Twitter!

Like this author's thread?

Get emails when @aedwardslevy has new unrolls!

Check out other threads from @aedwardslevy!

Read all threads by @aedwardslevy