Re: polls

[robert <http://dummy.us.eu.org/robert>]

 > From: Noelle <noelle>
 > Date: Wed, 13 Nov 2024 08:10:23 -0800 (PST)
 >
 > https://www.electoral-vote.com/evp2024/Items/Nov13-2.html

This sentence:

 the pollster would say: "We didn't try to predict who would win, we just
 predicted what ranges the two scores would fall in with 95% probability,
 and we did it."

is the key.  Basically, the result was like flipping a coin 7 times and
getting tails every time.  Not completely out of the realm of possibility.
And, Trump didn't even need to get tails ever time -- he just needed to do
it a few times.

But, I didn't know about the screening questions kicking so many people
out.  In general, I think people answer "no" when getting an unexpected
call, so it would probably make more sense to change the questions, e.g.,
"Are you planning to skip voting in the upcoming elections?" so the
respondent has to answer in the affirmative.  Might get better results --
who knows?

Nevertheless, this article doesn't address the elephant in the room: why
did fewer Harris supporters vote at all?  The stats are pretty clear about
that -- Trump got about the same number of votes, and Harris got fewer
than Biden.  Why didn't the polls account for that?