Poll results depend on pollster choices as much as voters’ decisions
An exercise in why you shouldn't worry too much about polls
https://goodauthority.org/news/election-poll-vote2024-data-pollster-choices-weighting/#disqus_threadOpen linkView original on lemmy.world
10 replies
Yes, but with a reputable pollster, questions and weighting are informed by historical data as much as possible.
Also, most of the good pollsters, who polled close to Election Day, tend to fall within or meet their margins of error when the final vote comes in. For as much as people like to complain about polls, I recommend that they go look at the big pollsters, and see how close they were right before an election.
The problem isn’t the polls, it’s that shit has been gerrymandered into a near 50/50 split and a winner is lost within the margin of error.
We still have polling conducted on the basis of who's going to pick up a cold call on their landline phone.
Who the fuck do you think is gonna pick a cold call up and talk to the weirdo who wants something from you at all, landline or no?
That’s one reason why most of these polls are garbage. I personally haven’t used a home landline phone since the 90’s.
Yeah but they adjust based on results, so they know for every person that says they're voting R on a landline there are 3 unreported D votes. There is a methodology further than writing down what people say.
I'm shocked they have enough that pick up any line given caller ID. Do a lot of people still answer an unknown call coming in and not let it go to voice mail?
Who the fuck still has a landline?
"We polled America by putting up a Facebook survey on this Boomer Facebook Group! Our data is sound!"
I’ll take “fucking duh” for $100, Alex.
😱
The news source of this post could not be identified. Please check the source yourself. Media Bias Fact Check | bot support