Register a SA Forums Account here!
JOINING THE SA FORUMS WILL REMOVE THIS BIG AD, THE ANNOYING UNDERLINED ADS, AND STUPID INTERSTITIAL ADS!!!

You can: log in, read the tech support FAQ, or request your lost password. This dumb message (and those ads) will appear on every screen until you register! Get rid of this crap by registering your own SA Forums Account and joining roughly 150,000 Goons, for the one-time price of $9.95! We charge money because it costs us money per month for bills, and since we don't believe in showing ads to our users, we try to make the money back through forum registrations.
(Thread IKs: weg, Toxic Mental)
 
  • Post
  • Reply
wesleywillis
Dec 30, 2016

SUCK A MALE CAMEL'S DICK WITH MIRACLE WHIP!!

Accipiter posted:

What needs to happen is that a totally unknown but actual good person needs to run on MAGA sensibilities. Appeal to the degenerates currently goose-stepping the right's ranks and adopt the current flock by whatever means necessary to propel themselves to victory.

Then once in office, do a complete 180 and enact the most liberal and progressive policies which have, to borrow an aphorism, never been seen before in this country and perhaps in history.

Yeah, can you believe that it's been like 40+ years since someone even tried to kill a president?

Adbot
ADBOT LOVES YOU

3 DONG HORSE
May 22, 2008

I'd like to thank Satan for everything he's done for this organization

Mistle posted:

Not a fart or gastroenterology expert, but I would guess Biden has gas from all the dairy in the ice cream he eats.

You are weak if dairy makes you fart.

redshirt
Aug 11, 2007

NEELIX 28!

dervival
Apr 23, 2014

QuarkJets posted:

jared kushner brought peace to the middle east and i can't believe that joe biden was able to undo it all so fast

i can't believe joe biden undid bush's may 2003 victory in iraq too

pig labeled 3
Jan 3, 2007

3 DONG HORSE posted:

You are weak if dairy makes you fart.

Reported for ableism

Bone Crimes
Mar 7, 2007

ragnarokette posted:

You're in the ballpark but statistics is just brain melting like that sometimes.

So the first step is they build a panel, which is theoretically demographically identical or very close to that of what they are trying to model. This is really hard to do though for reasons you probably expect, it can be hard to find members of smaller demographics that are willing to participate in the first place. Depending on how they recruited the panel it could be a very significant way of throwing everything off down the line with compounding errors, which, given this has Jill Stein at 3% nationally is my initial hunch.

In the context of political polling I'm guessing they struggle particularly with the following, let alone trying to find people who tick multiple for cross tabs and such:
  • young people
  • low income people
  • queer people
  • racial and religious minorities

From there you can sample randomly and it actually takes way fewer samples than you'd think for the sample mean to start to converge to the population mean (in this case the panel). Somehow laypeople have gotten it into their heads that anything less than like.... tens of thousands is a small sample size when really you start to get pretty close to the population mean with a hundred samples or less per the central limit theorem I alluded too previously. Larger sample sizes basically give you diminishing returns on how close your sample mean gets to the population mean. There are a couple implicit assumptions statistically that go along with that. Namely that your sampling is normally distributed, which I'm not going to check but nature loves a normal distribution so it's incredibly likely and given that its an industry standard technique I'm guessing it is. The other big one, and is another potential pitfall here, is that samples should be independent from each other. This actually may not necessarily be the case with voter opinions compared to a discrete, binary event like watching a TV show or not.

Once you do all this, you have some weighting factor to scale your panel sample up to the population level. Basically this is just a big multiplying factor per person.

Statistically everything they've done in that blurb is standard practice, it's what Neilsen has done for years to measure TV viewership. I actually worked on a project to emulate them a couple years ago. To give you a real world example of how easily this can go wrong, our initial panel beta testers were almost all people who worked for my previous large international manufacturing conglomerate that is mostly known in the west for electronics. We were massively over represented for middle aged, upper class white people because those are who works in ad tech. We had I want to say like.... ten users total in the initial rounds that were both younger and lower income. But we still have to scale that back up to the population, which means that one individual gets a much larger relative scaling factor. This lead to a couple cases where we would "find" things like every single zoomer watched Random Bullshit Show, but really all that happened was two of them watched it and our initial data was heavily skewed.

I hope I've explained this well I really didn't want to effortpost about statistics and polling for a project that I've mostly tried to delete from my memory.

I appreciate this effort post, but I think there are still a bunch more biases that are implicit in this approach. All of this methodology is due to the fact that they cannot get a random sample, don't want to pay for a random sample, and now in 2024 it's even worse. If a sample of 1000 people was truly random, you would not need any model or other technique to 'correct' the numbers for the U.S. voting population. You wouldn't need to struggle to find young/queer/minority people.


ragnarokette posted:

Namely that your sampling is normally distributed, which I'm not going to check but nature loves a normal distribution so it's incredibly likely and given that its an industry standard technique I'm guessing it is.

I think this is very, very untrue, and has been getting so bad recently that it could be the main cause of the issue here. If a phone call, who picks up? Who has a phone? Who stays on to answer questions? How did you find the number? Did they lie about their demographics/voter status, or do you have that data via another means? When in the day did you call? Did you call from a number known to be a scam?
I realize this CNN example is different, but the same sort of thing applies, who is going to be on this panel? is that random?

I don't know exactly, but someone said in one of these threads that the response rate for a cold polling call is less than 1%. Which, lol, good luck saying that's a representative sub-sample of a population. I mean maybe of the dumb-rear end, will answer any random number demographic.

Another thing is that there is an implicit assumption that there are demographic features that can be known about voters, that there are sub-populations of voters with these demographics that vote similarly, and that we can identify them via questions determined a priori. Some of these might be true, but when we are talking about a bloc like 'young voters' or 'minority 1' is that a good bloc that votes similarly enough to allow you to take a sample of them and interpolate? Who decided that? Was that before or after event x happened and that bloc split? Did you specify enough demographic classes to get a good model, and few enough that you have valid numbers for cross-tabs to inform your model?

All is BS methodology crap seems to get you any answer you want. Which sure, that's always been true, but I think now we are seeing such huge differences between polls of the same race, and between polls and reality that I wonder at WTF people at CNN or whatever are doing. It sure seems like the polling world is flushing any credibility it had down the drain. Sorry, this might have come off harsh, but this poll thing really sticks to me. I want good info about these races, but there just isn't any.

Lammasu
May 8, 2019

lawful Good Monster

lilljonas posted:

Well I can't remember Israel ever being this mask off genocidal in decades, so Biden not doing anything about it and just shipping more bombs to Israel daily means that he deserves to be called out on it.

Yes, the second US withdraw their support, Israels current defence policy becomes impossible.

And then Israel gets invaded.

redshirt
Aug 11, 2007

So does anyone believe the possibility these polls are correct, and Trump is in the lead?

Jet Jaguar
Feb 12, 2006

Don't touch my bags if you please, Mr Customs Man.



redshirt posted:

So does anyone believe the possibility these polls are correct, and Trump is in the lead?

Other than the fact we live in the dumbest possible timeline?

Though again, how Kennedy (who isn't even gonna be on the ballot in several states, I imagine) takes 15% from Biden is a bit of a stretch for me.

War Wizard
Jan 4, 2007

:)

redshirt posted:

So does anyone believe the possibility these polls are correct, and Trump is in the lead?

I believe polls are selectively chosen for which can be sensationalized the most. Unless you're next to Trump, in which case you grab any "poll" that says he's the specialist boy ever.

Ghostlight
Sep 25, 2009

maybe for one second you can pause; try to step into another person's perspective, and understand that a watermelon is cursing me



Bone Crimes posted:

If a sample of 1000 people was truly random, you would not need any model or other technique to 'correct' the numbers for the U.S. voting population. You wouldn't need to struggle to find young/queer/minority people.
You have to have a model precisely because the sampling is random and you're trying to match it with the population of the United States, which is not.

Agents are GO!
Dec 29, 2004

redshirt posted:

Let's all stop gaslighting each other and accept the reality that Trump is somehow ahead in the polls.

no

The Locator
Sep 12, 2004

Out here, everything hurts.





dervival posted:

have your in-laws heard literally nothing about project 2025

if they really think that someone that's the focal point of that poo poo is exactly the same as the current guy then they're really loving clueless

The true believers will argue that Project 2025 is a Dem false flag thingie. They will not own it, even while espousing many of the things that are contained in that plan. At the same time they'll call the left "communists" who want to control every aspect of your life.

birds
Jun 28, 2008


I don’t think the general U.S population is very aware of the legal issues Trump faces still. That’s why I can believe he’s ahead.

PuttyKnife
Jan 2, 2006

Despair brings the puttyknife down.

Waltzing Along posted:

I'm poo poo posting

Nice! I'm posting while I poo poo.

kazil
Jul 24, 2005

Derpmph trial star reporter!

Trump is going to win Puerto Rico


Funky See Funky Do
Aug 20, 2013
STILL TRYING HARD

redshirt posted:

So does anyone believe the possibility these polls are correct, and Trump is in the lead?

I entertain the possibility. Like I always say - America didn't get either smarter or saner since they elected him the first time.

Probably not though.

Bottom Liner
Feb 15, 2006


a specific vein of lasagna

Funky See Funky Do posted:

I entertain the possibility. Like I always say - America didn't get either smarter or saner since they elected him the first time.

Probably not though.


All of the elections post 2016 have leaned harder blue than anyone could have predicted, including some historical victories in an off cycle year. A lot of red voters died from covid and a lot of blue voters are more engaged than ever because they're pissed. Add to that roe v wade and all the abortion poo poo, and '24 will likely be a landslide compared to '20.

Anything can happen, but the winds are definitely blowing pretty hard in favor of Trump getting his poo poo kicked in.

Small Strange Bird
Sep 22, 2006

Merci, chaton!

3 DONG HORSE posted:

You are weak if dairy makes you fart.
I heard this in Worf's voice.

eke out
Feb 24, 2013



Bone Crimes posted:

I wonder at WTF people at CNN or whatever are doing. It sure seems like the polling world is flushing any credibility it had down the drain. Sorry, this might have come off harsh, but this poll thing really sticks to me. I want good info about these races, but there just isn't any.

also, with all due respect to the pollsters, you can look at a poll where trump wins women +1 and instantly dismiss it lol (not to mention winning 18-29s significantly, but at least i understand those are harder to find and there are a lot fewer of them in your sample so weighting can make your numbers less realistic)

Agents are GO!
Dec 29, 2004

The only polls worth paying attention to right now are actual special elections.

redshirt
Aug 11, 2007

Until Trump is dead and in the ground, I trust no poll

free hubcaps
Oct 12, 2009

redshirt posted:

Until Trump is dead and in the ground, I trust no poll

Trump just died:banjo:

(USER WAS PUT ON PROBATION FOR THIS POST)

Buce
Dec 23, 2005

kazil posted:

Trump is going to win Puerto Rico




:shobon:

poisonpill
Nov 8, 2009

The only way to get huge fast is to insult a passing witch and hope she curses you with Beast-strength.


No matter what happens, literally no matter what, Trumpnwill claim that Biden rigged the voting machine or something

smoobles
Sep 4, 2014

free hubcaps posted:

Trump just died:banjo:

First I'm hearing this

sharknado slashfic
Jun 24, 2011

Fun anecdote, having dinner with the fam and mom and grandmom were complaining loudly that their Republican Primary ballot didn't have party designations so they didn't know who to vote for besides Trump. Larry Hogan eventually got a vote on name recognition.

How is it possible to consume the news all day and not know anything about your home state or that Trump and Hogan famously don't get along.

redshirt
Aug 11, 2007

free hubcaps posted:

Trump just died:banjo:

NUB NUB!

Goatse James Bond
Mar 28, 2010

If you see me posting please remind me that I have Charlie Work in the reports forum to do instead
Hogan? The wrestler?

Magnetic North
Dec 15, 2008

Beware the Forest's Mushrooms

Bottom Liner posted:

All of the elections post 2016 have leaned harder blue than anyone could have predicted, including some historical victories in an off cycle year. A lot of red voters died from covid and a lot of blue voters are more engaged than ever because they're pissed. Add to that roe v wade and all the abortion poo poo, and '24 will likely be a landslide compared to '20.

Anything can happen, but the winds are definitely blowing pretty hard in favor of Trump getting his poo poo kicked in.

Yes, yes, but have you considered that we're doomed? Doomed, I say.

Pook Good Mook
Aug 6, 2013


ENFORCE THE UNITED STATES DRESS CODE AT ALL COSTS!

This message paid for by the Men's Wearhouse& Jos A Bank Lobbying Group

eke out posted:

also, with all due respect to the pollsters, you can look at a poll where trump wins women +1 and instantly dismiss it lol (not to mention winning 18-29s significantly, but at least i understand those are harder to find and there are a lot fewer of them in your sample so weighting can make your numbers less realistic)

Very correct take. Trump ain't winning women or the youths.

sharknado slashfic
Jun 24, 2011

Goatse James Bond posted:

Hogan? The wrestler?

They'd probably vote for him

Waltzing Along
Jun 14, 2008

There's only one
Human race
Many faces
Everybody belongs here
The one thing that Trump sort of has in his favor is the massive inflation we are seeing due to corps going gloves off with constantly raising the prices on everything. The news media is just reporting on the high prices but not on the massive profits they are pulling in. It's like they figured out that they can just go crazy with prices and no one will do anything about it and at the same time blame biden in the hopes of trump dropping taxes a ton again.

It's loving disgusting. If this country had any actual means or desire to maintain prices, Biden would win with 400+ EVs.

Stoatbringer
Sep 15, 2004

naw, you love it you little ho-bot :roboluv:

free hubcaps posted:

Trump just died:banjo:

Yuck!

Stoatbringer
Sep 15, 2004

naw, you love it you little ho-bot :roboluv:

3 DONG HORSE posted:

You are weak if dairy makes you fart.

Farting is fun, Captain Buzzkill.

Altared State
Jan 14, 2006

I think I was born to burn

redshirt posted:

Nervous about these poll numbers? What are you doing specifically to help? Are you donating money? Are you making calls/donating time? Are you working with a campaign?

Do something!

lol

Like any of that is gonna change things

redshirt
Aug 11, 2007

Altared State posted:

lol

Like any of that is gonna change things

So, nothing means anything, nothing matters. Correct?

Bone Crimes
Mar 7, 2007

Ghostlight posted:

You have to have a model precisely because the sampling is random and you're trying to match it with the population of the United States, which is not.

Huh? Isn't the whole point that a sufficiently large random sample of a heterogeneous population trends to the mean of that population? a large random sample should catch the same percentage of whatever group within statistical polling error. If you have a poll where you have 1% young voters, but those voters make up 20% of the electorate based on the actual results or polling records, you don't have a random sample.

BrigadierSensible
Feb 16, 2012

I've got a pocket full of cheese🧀, and a garden full of trees🌴.

frytechnician posted:

Yeah, wrote that poorly. I meant to infer that Obama took shots at Trump and even though they were incredibly soft touch, he still lost his mind that he was taunted by the charismatic black man in front of everyone. I often write how I talk, which is to say kind of sloppily.

Whilst what you say is true, I tend to think of if/interpret it ever so slightly differently.

Trump holds his petty grudge against Obama so fervently not only because Obama gently made un of him. (Although that is a big part of it), but also because Obama was not bothered by, and shrugged off and chuckled at Trump's hate filled invective and campaign of "Show us the birth certificate you dark skinned foreigner!!!"

To Trump's mind this was an unforgivable disrespect, because it meant he was not important, he was not big, he was not the powerful important, respectable, influential newsmaker that he needs to think he is. If a *gasp* black man can so easily brush off his attacks and not be bothered by them, then that means he is weak and powerless and an inconsequential figure of fun.

This will not stand!

Adbot
ADBOT LOVES YOU

Philthy
Jan 28, 2003

Pillbug

redshirt posted:

So does anyone believe the possibility these polls are correct, and Trump is in the lead?

No. These same polls have been showing Republicans winning all their elections with +10, +20, and higher and they keep losing to Democrats. Any time a MAGA goes to bat, they get creamed. Trump is pure cancer when it comes to voters.

It's made up horse race bullshit.

  • 1
  • 2
  • 3
  • 4
  • 5
  • Post
  • Reply