From the Democratic firms& #39; assessment of 2020 polling error: I find this piece particularly vindicating. I& #39;ve been saying from the start that likely voter modeling is part of the issue.

https://www.democracydocket.com/2021/04/revisiting-polling-for-2021-and-beyond/">https://www.democracydocket.com/2021/04/r...
People ignored me and preferred to listen to louder [male] voices saying it& #39;s all sample. It IS *also* sample. But it is also that we cannot predict a population that doesn& #39;t exist yet!!!

I& #39;m glad this is starting to get out there. Never rely on people who don& #39;t show their work.
If campaign polls using extensive histories have these problems, it& #39;s likely magnified in public polls not using registration data.
This point is also extremely important: We don& #39;t want to overcorrect. There& #39;s something about Trump on the ballot here, and we& #39;ll need to know how that impacts us all moving forward.
To clarify, they do say they think the sample/measurement error is larger than the turnout error. My point has been that it& #39;s both, and I& #39;ve been written off for saying that. They are also saying it& #39;s both.
You can follow @nataliemj10.
Tip: mention @twtextapp on a Twitter thread with the keyword “unroll” to get a link to it.

Latest Threads Unrolled: