Welcome to DU! The truly grassroots left-of-center political community where regular people, not algorithms, drive the discussions and set the standards. Join the community: Create a free account Support DU (and get rid of ads!): Become a Star Member Latest Breaking News Editorials & Other Articles General Discussion The DU Lounge All Forums Issue Forums Culture Forums Alliance Forums Region Forums Support Forums Help & Search

General Discussion

Ms. Toad

(37,984 posts)

14. They are based on data -

Reply to gab13by13 (Original post)

Thu Nov 6, 2025, 12:03 AM

Nov 6

BUT - since they are not asking every single person, they are an extrapolation (interpretation) from the actual data mapped against the population as a whole.

How accurate that extrapolation depends on how well those sampled model the population as a whole, and how accurate the adjustments made for over/under sampling certain populations are.

It's sot of like flipping a coin 10 times and getting 3 heads and 7 tails, then extrapolating from that that if the coin were flipped a million times 300,000 would be heads and 700,000 would be tails - when the reality is that with a million flips (assuming a balanced coin and uniform flipping) the numbers would be closer to 500,000-500,000.

That's an over-simplification - but that's the gist of how extrapolations from actual data (the number of heads in a limited sample) might not match the actual results.

Edit history

Please sign in to view edit histories.

Recommendations

3 members have recommended this reply (displayed in chronological order):

Prairie_Seagull ProfessorGAC susanr516

31 replies

= new reply since forum marked as read

Highlight:

Lol, Nate Silver Says Polls May Be Overestimating Trump [View all] gab13by13 Nov 5 OP

Other than endorsing Cuomo, it didn't seem like Musk was involved in yesterday's election Blue Owl Nov 5 #1

You have a link to what Silver said and the context? LearnedHand Nov 5 #2

It scrolled across my home page. gab13by13 Nov 5 #8

M Cohen said Pisswig purchased poll results dweller Nov 5 #3

Here is an expert on the subject BootinUp Nov 5 #4

Here is Morris's new polling site: Fiendish Thingy Nov 5 #10

According to his chart there's a vergence in the force (trumps approval numbers). nt BootinUp Nov 5 #11

Could you translate that into English for me? Fiendish Thingy Nov 5 #12

Its a real phrase from The Phantom Menace. I am mis-using it to refer to BootinUp Nov 6 #13

Quoting from the prequels... Fiendish Thingy Nov 6 #19

Oh, I don't know about all that. Nt BootinUp Nov 6 #21

I've Watched Episode 3 Multiple Times ProfessorGAC Nov 6 #24

If you're a casual fan who can endure multiple viewings of Episode 3... Fiendish Thingy Nov 6 #25

I Was Ok With The Latter ProfessorGAC Nov 6 #27

Andor is the prequel story to Rogue One Fiendish Thingy Nov 6 #28

Vaguely Recall That ProfessorGAC Nov 6 #29

The second and final season of Andor just came out a couple of months ago. Fiendish Thingy Nov 6 #31

This is how Newsweek quoted Silver. Silent Type Nov 5 #5

Polls make estimates about the makeup of the electorate based on previous elections EdmondDantes_ Nov 5 #6

So much winning? Drum Nov 5 #7

Corrupt failure says what? Fiendish Thingy Nov 5 #9

They are based on data - Ms. Toad Nov 6 #14

Seems that for several years the pollsters Old Crank Nov 6 #15

A bit? malaise Nov 6 #16

well, I totally agree with you about the polls. raccoon Nov 6 #17

Of course the poll itself doesn't overestimate. It's just a poll. Clearly he's referring to ... QueerDuck Nov 6 #18

Modeling is used, so there "weighted" aspects to polling. Jbraybarten Nov 6 #20

When the questions are slanted Prairie_Seagull Nov 6 #22

Things that make your head explode LR3 Nov 6 #23

In election season pollsters are supposed to only measure likely voters Justice Brandeis Nov 6 #26

There are many polls. Pick the one you like and swear by it. Swear at the others. Norrrm Nov 6 #30