Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

One pollster’s explanation for why the polls got it wrong

vox.com

Post reply on HN
Print view View original

381–390 of 565 posts

Re: One pollster’s explanation for why the polls got it wrong

#381

Post by _AzMoo »

recursive wrote: post #163
throwaway201103 wrote: post #102

Earlier quoted context omitted.

Considering the trend for people to be socially canceled, scorned, and shamed for supporting the "wrong" candidate, yes I think exit polling (and all polling for that matter) are not working. People are much more likely to either decline to respond, or they will lie.

I think mail-in ballots are a much bigger problem for exit polling than fear of being cancelled. I cite no sources, just a hunch.

They are actually both problems. The fear of being "cancelled" due to poll responses is called the Bradley Effect and definitely does apply to exit polls: https://en.wikipedia.org/wiki/Bradley_effect#Exit_polling

Re: One pollster’s explanation for why the polls got it wrong

#382

Post by colinmhayes »

ineedasername wrote: post #362
colinmhayes wrote: post #354

Earlier quoted context omitted.

But the reason they're not taking the poll is because they don't want to admit support for Trump, right? Of course some are happy to tell everyone, but some aren't. Otherwise why is this concept of republicans responding to polls less just starting now with Trump?

No, not if the hypothesis of the article is correct: They have lower social trust & cooperation metrics, and are disinclined to answer any polls. As for why it started with Trump, there could be a few reasons, all speculation on my part: He may be attracting people who didn't vote much before, and these new voters are the sorts of people who have lower trust etc., and so don't answer polls. Personally though, I think…

Yea I agree, they need to find a new term I guess because it seems pretty clear that this is what's been happening to me at least. I guess my question was more along the lines of who doesn't think this was the issue? Seems so obvious that his conspiracy theory squad won't want to talk to pollsters. Plus energized dems are more willing than usual to talk. The 1% response rate is a crazy number. How could they possibly think they're getting a representative sample if only 1% of people respond and responding is a choice? If there's any correlation between predisposition to respond and preferred candidate they're fucked. And it's hard to believe there wouldn't be.

Re: One pollster’s explanation for why the polls got it wrong

#383

Post by masonic »

dragonwriter wrote: post #83
bryanlarsen wrote: post #74

Earlier quoted context omitted.

There aren't many people with $100 million income. Most billionaires don't have income that high -- there is a much higher wealth disparity than there is income disparity. So while I'd rather the media reported the median income than the median income, it's the number we have and hopefully it's a useful approximation.

> There aren't many people with $100 million income Sure, but there's also a couple with over an order of magnitude more . > So while I'd rather the media reported the median income than the median income, it's the number we have and hopefully it's a useful approximation. It's not a useful approximation of anything, and we have a lot more detailed information that “average income of voters of one side vs. the other"…

  Sure, but there's also a couple with over an order of magnitude more.
Who has an income of more than $1 billion a year?

Re: One pollster’s explanation for why the polls got it wrong

#384

Post by disown »

I wonder what Facebook or Google's "poll" numbers would have been if they decided to run one? Given their access to search, texts, social media posts, emails, tracking, etc along with their profile of a large segment of the population, I'm guessing their polling data would be the most accurate.

Re: One pollster’s explanation for why the polls got it wrong

#385

Post by majormajor »

kaitai wrote: post #360
adventured wrote: post #333

Earlier quoted context omitted.

> The bulk of Trump voters are from rural areas, and tend to be less (or un-)educated. You're of course ignoring even worse problems on the Democrat side. The lowest education rates and highest drop-out rates in the US are not in rural areas, they're almost exclusively in the inner cities where Democrats tend to completely dominate the vote. Rural students at 87% are more likely to graduate from high school in four y…

I feel like your answer is sort of in bad faith. I live in an urban area, and people are quite concerned about the dropout rate (and more to the point that I think you're trying to imply but are dancing around for your own reasons, the racial achievement gaps). But I guess we put a different spin on it: we are ashamed of it, we should be ashamed of it, and we bring it up a lot in political races and on billboards and…

In sports terms, if a penalty is committed, we give the other team some compensation. Like a pass interference penalty. Because it's not fair to make a team go for the same goal when they've gotten cheated...

In the US, we scream bloody murder at most attempts to even out those starting point disparities that our ancestors caused... when I was in school, one favorite trick to do instead was to stick Magnet programs in poor schools to import kids from the rest of the city to try to bring up some of the numbers, rather than focusing on the kids who weren't doing well in the first place.

It makes for a wonderful self-fulfilling "these people are worth less because they accomplish less so it's out of our hands so we have no need to try to make right our past wrongs" story.

Re: One pollster’s explanation for why the polls got it wrong

#386

Post by burlesona »

> Qualitative research doesn’t solve the problem of one group of people being really, really excited to share their opinions, while another group isn’t. As long as that bias exists, it’ll percolate down to whatever you do.

Pretty good TLDR from the end of the article.

Re: One pollster’s explanation for why the polls got it wrong

#387

Post by boomboomsubban »

ineedasername wrote: post #343
boomboomsubban wrote: post #331

Earlier quoted context omitted.

>Violence was instigated on both sides, but regardless of what the underlying reality was, the perception was that leftists were responsible for much of the violence, and that is problematic electorally. Literally "it doesn't matter who was responsible for the violence, the left get blamed for it so it's their fault." Fuck that. The police are very often responsible for the violence, and you should not stop protestin…

I don't think they were saying the protests should stop. They made on observation about how the protests were perceived by others , and that perception, correct or not, influenced voting decisions.

This is changing it from "they said to stop" to "they said it was wise to stop," and the distinction basically only matters if you want the Democrats to win. You're saying the same thing either way.

Re: One pollster’s explanation for why the polls got it wrong

#388

Post by devinplatt »

euank wrote: post #287
DecoPerson wrote: post #261

“The kind of people who answer polls are really weird, and it’s ruining polling.” This is true everywhere. I’ve been involved polling in for a popular AAA game, a small retail business, school events, online forums, and more; they all fail to account for the “who chooses to answer” bias (is there a name for this?). I speculate that the “average 4.7 million viewers“ rating Firefly received when it aired was totally of…

> is there a name for this bias? I think it's response bias. https://en.wikipedia.org/wiki/Response_bias

I think actually op is referring to https://en.wikipedia.org/wiki/Participation_bias: "Participation bias or non-response bias is a phenomenon in which the results of elections, studies, polls, etc. become non-representative because the participants disproportionately possess certain traits which affect the outcome."

Confusing terminology, but I guess "response bias" is about a false response by the participant to a question, and "non-response bias" is about whether the selected participant responded (participated) at all.

Re: One pollster’s explanation for why the polls got it wrong

#389

Post by tshaddox »

orangecat wrote: post #345
tshaddox wrote: post #309

Earlier quoted context omitted.

Oops, not sure where I found that Missouri figure, but it looks like you're right. Still, one quarter to one third of the population doesn't fit what I would remotely consider to be "elite." And why is "almost everyone in your social circle" relevant? I don't think people generally use the word "elite" to refer to the ability to make friends from among a specific third of the national population.

Still, one quarter to one third of the population doesn't fit what I would remotely consider to be "elite." And why is "almost everyone in your social circle" relevant? It's one thing if you have a college degree and half of your acquaintances don't. It's another if you rarely have meaningful interactions with anyone who doesn't; in that case you're in a subculture that has very different experiences than the average…

Okay, I’m on board with “very different experiences than the average American,” but that’s not what “elite” means.

Re: One pollster’s explanation for why the polls got it wrong

#390

Post by fiblye »

mastazi wrote: post #244

This is my personal experience: over the course of my life, I have held both conservative positions and more progressive ones (depending on the topic, and in different periods of my life). I have always been much more willing to discuss openly those positions that I would describe as progressive. This is despite the fact that over the years I have been living in more than a handful of different countries, each one wi…

I think it also depends on the audience and group you're with. If you're moving around a lot, you might end up in expat/international/diverse groups. Most people who move to several countries aren't moving to villages 4 hours from a city and speaking and blending in with the locals and really hearing what rural people think.

Growing up in a small town and moving between small towns across the US every year or so, I never had exposure to "liberals" until I started using the internet as a teen. Until then, everyone I was ever around talked about them like they were bogeymen.

In the country I live in now, I was initially exposed to much more "progressive" opinions from people. Now I'm seen as less "that foreign guy" and more of a local, and I hear what people would normally discuss with their friends and family. It's quite different.

Post reply on HN