I think this is pretty fascinating. I follow a couple of guys who are in the business, and able to analyze polls by looking at their cross tabs. Apparently, a poll of young people just released shows Biden only leading Trump by 4 points. But the raw results weren’t that, they collect raw results, evaluate their sample, and then “weight” it to correct for sampling errors. (I think I have this more or less correct - happy to be corrected if someone knows better). Evidently this poll released the unweighted results accidentally and then released the weighted results later. Pollers won’t always provide that information, so it is nice to get that.
Political Polling Thread (2 Viewers)
- Thread starterMT15
- Start date
- Latest activity Latest activity:
Users who are viewing this thread
samiam5211
Well-known member
Offline
I was talking about Vermont.
It is clear that in Vermont there were a ton of Dems voting for Hailey just from looking at the total turnout compared previous primaries.
2024 South Carolina Republican Presidential Primary Polls | RealClearPolling
Explore poll data on the 2024 South Carolina Republican Presidential Primary. Uncover trends and gain insight into electoral dynamics for key races and decisive outcomes.
In South Carolina, the result was within the margin of error for the RCP average.
- Thread starter
- #20
OP
OP
MT15
Well-known member
Online
So are you saying that polls are accurate? Because this whole thread is full of examples of Trump and the GOP underperforming their polls.I was talking about Vermont.
It is clear that in Vermont there were a ton of Dems voting for Hailey just from looking at the total turnout compared previous primaries.
2024 South Carolina Republican Presidential Primary Polls | RealClearPolling
Explore poll data on the 2024 South Carolina Republican Presidential Primary. Uncover trends and gain insight into electoral dynamics for key races and decisive outcomes.www.realclearpolling.com
In South Carolina, the result was within the margin of error for the RCP average.
I agree about Vermont, though. Still the record of polling these last few years is not good.
samiam5211
Well-known member
Offline
I think the polls do exactly what they should. They are a snapshot in time, and give a pretty good idea of what people are thinking at that moment.
I do think that people have misplaced expectations about what polls do.
Even in 2016, the polls weren't really far off. Every state that Hillary unexpectedly lost was within the margin of error of the polls.
People shouldn't expect polls to exactly pick the winner in cases where the outcome of the election is going to be closer than 3 or 4 points.
- Thread starter
- #22
OP
OP
MT15
Well-known member
Online
Agree with all that, but what is fascinating are the final polls before elections being off by more than the margin of error. This has happened repeatedly since 2016. I’m not talking about the 2016 election, although I would have to check what you said, because I am not sure that polls were that accurate. After 2016, many final polls show the GOP underperforming when votes are actually cast.
Take a look at the final RCP polls posted above for the 2020 midterm. They were off.
samiam5211
Well-known member
Offline
The polls for the 2022 mid terms weren't really off though.
They were almost all within the margin of error. There were certainly a couple where democrat turnout was underestimated, but for the most part the polls were within the margin if error.
People using the polls to predict a red wave were wrong, because many of the seats they were predicting, were closer than the margin of error.
Taurus
Well-known member
Offline
They've been consistently wrong within the margin of error in the same direction for three election cycles in a row, though.
Might want to nudge the starting point a little.
If every shot I fire hits 2" low, I don't think to myself "That's still a pretty good group." I aim 2" higher.
samiam5211
Well-known member
Offline
They have not been wrong within the margin of error for the past three election cycles.
The polls are great at what they do. People just seem to have unrealistic expectations of what the polls are supposed to measure.
When i refer to "the polls' I am talking about the average of the polls, not any individual poll.
Something like the RCP average.
538 is terrible IMO. It is just Nate Silver making guesses based off of polls. He got famous for saying Hillary was in trouble in 2016, but he's not some incredible mind.
Last edited:
- Thread starter
- #26
OP
OP
MT15
Well-known member
Online
I don’t think RCP was within the margin of error a lot of the times. It’s not easy to find what they consider their margin of error and maybe they don’t have one, since they are an average of other polls.
Take Fetterman in PA for example. They had Oz slightly ahead by 0.4 and taking the seat. Fetterman won by 4.9%. That’s a 5.3% difference and is probably more than the margin of error would be.
Take Murray in WA. RCP had Murray winning by 3.0%, and at one point had classified it as a tossup, so that is probably considered to be within their margin of error. She won by 14.5%.
Overall they forecast the Rs taking back the Senate by 53 to 47. These aren’t insignificant errors.
You can see their final forecasts and the actual results here for the Senate. The House was worse.
Take Fetterman in PA for example. They had Oz slightly ahead by 0.4 and taking the seat. Fetterman won by 4.9%. That’s a 5.3% difference and is probably more than the margin of error would be.
Take Murray in WA. RCP had Murray winning by 3.0%, and at one point had classified it as a tossup, so that is probably considered to be within their margin of error. She won by 14.5%.
Overall they forecast the Rs taking back the Senate by 53 to 47. These aren’t insignificant errors.
You can see their final forecasts and the actual results here for the Senate. The House was worse.
- Thread starter
- #27
- Thread starter
- #28
- Thread starter
- #29
Luntz is an agitprop provocateur. His sole purpose is to spin Republican talking points and push for voter suppression. That is not meant as an insult to you, MT15.
As for polls? They are bullschlitz. Particularly exit polls are bullschlitz. What polls do is keep everyone in a constant state of agitation and anxiety.
Furthermore, in point of opinion, the parties should do away with primaries. Whoever wants to run for a statewide election can get signatures to get on the ballot. They would have hold multiple town halls to discuss policy ideas, their finances would have to be open to scrutiny. They could not put in more than a certain amount of their own money into their campaign. All campaign contributions would have to be made public. On the election for president the conventions would choose the candidate. Again complete transparency would be required for policies, financials and campaign donations. All PACs and Super-PACs would be eliminated. Party finances would be required to be transparent including donation information.
I realize this is wishful thinking but our politics has come down to screaming skirmishes of misinformation, disinformation and outright lying.
Oh, and eliminate the Electoral College. States do not vote. People vote. If you want to gain people’s votes then a candidate would have to explain their policies.
zztop
Well-known member
Offline
Saw this article on the oddity of polling
Something weird is happening beneath the overall stability of the early 2024 polling — and it’s either a sign of a massive electoral realignment, or that the polls are wrong again
Something weird is happening beneath the overall stability of the early 2024 polling — and it’s either a sign of a massive electoral realignment, or that the polls are wrong again
Taurus
Well-known member
Offline
Huh. And yet women both young and old, have smashed the GOP in every election since Dobbs.
So we're supposed to believe that these same young women who're flipping red districts and voting for abortion rights by overwhelming margins are suddenly in full-throat support of Trump?
Really?
Dear pollsters, I know you want to keep getting paid, it's totally understandable but JFC you're simply stealing now.
Optimus Prime
Well-known member
Online
Opinion polling has no lazier cliché than “snapshot in time.”
The aphorism is intended to suggest impermanence — that polls taken weeks or months before an election have limited predictive value. The phrase has been repeatedly invoked as the 2024 presidential election race has unfolded. It will be heard many times before the campaign ends.
All too often, “snapshot in time” is a convenient tactic for commentators and politicians to scoff at or dismiss poll results that contradict their partisan preferences.
More commonly, the phrase is a refuge or metaphoric shield for pollsters when their pre-election surveys misfire. In such cases, “snapshot in time” is cited in attempting to defend or rationalize polls that careen well off-target, as many of them did in the 2020 presidential election.
Joe Biden was elected to the presidency four years ago by margins well short of the double-digit blowout suggested by the polls of CNN, Quinnipiac University, Economist/YouGuv and NBC/Wall Street Journal. Those polls estimated Biden’s end-of-campaign lead at 10 to 12 percentage points over then-President Donald Trump.
Biden won the popular vote by 4.5 points.
The discrepancy in 2020 between election results and polls overall was the most pronounced in 40 years, and prompted characterizations that the outcome was a “train wreck” and “a disaster for the polling industry,” as David A. Graham wrote in the Atlantic.
Graham’s essay anticipated the “snapshot-in-time” defense favored by pollsters, writing: “If their snapshots are so far off, where were they aiming the lens? Why bother?” He noted that “the public uses opinion polls to try to understand what happens [in elections]. If the polls and their analysts don’t offer the service that customers are seeking, they’re doomed.”
Polls surely are not doomed, as their ubiquity in the 2024 election cycle attests.
But the ubiquity of polls does pose a challenge to validity of the “snapshot in time” cliché. The sheer number of polling “snapshots” form a panorama that can offer useful insights about a presidential race. The panorama has, for many months now, signaled that the 2024 race could be close, that no landslide lies ahead, and that decisive battleground states where the election may pivot have been leaning toward Trump..............
The aphorism is intended to suggest impermanence — that polls taken weeks or months before an election have limited predictive value. The phrase has been repeatedly invoked as the 2024 presidential election race has unfolded. It will be heard many times before the campaign ends.
All too often, “snapshot in time” is a convenient tactic for commentators and politicians to scoff at or dismiss poll results that contradict their partisan preferences.
More commonly, the phrase is a refuge or metaphoric shield for pollsters when their pre-election surveys misfire. In such cases, “snapshot in time” is cited in attempting to defend or rationalize polls that careen well off-target, as many of them did in the 2020 presidential election.
Joe Biden was elected to the presidency four years ago by margins well short of the double-digit blowout suggested by the polls of CNN, Quinnipiac University, Economist/YouGuv and NBC/Wall Street Journal. Those polls estimated Biden’s end-of-campaign lead at 10 to 12 percentage points over then-President Donald Trump.
Biden won the popular vote by 4.5 points.
The discrepancy in 2020 between election results and polls overall was the most pronounced in 40 years, and prompted characterizations that the outcome was a “train wreck” and “a disaster for the polling industry,” as David A. Graham wrote in the Atlantic.
Graham’s essay anticipated the “snapshot-in-time” defense favored by pollsters, writing: “If their snapshots are so far off, where were they aiming the lens? Why bother?” He noted that “the public uses opinion polls to try to understand what happens [in elections]. If the polls and their analysts don’t offer the service that customers are seeking, they’re doomed.”
Polls surely are not doomed, as their ubiquity in the 2024 election cycle attests.
But the ubiquity of polls does pose a challenge to validity of the “snapshot in time” cliché. The sheer number of polling “snapshots” form a panorama that can offer useful insights about a presidential race. The panorama has, for many months now, signaled that the 2024 race could be close, that no landslide lies ahead, and that decisive battleground states where the election may pivot have been leaning toward Trump..............
Create an account or login to comment
You must be a member in order to leave a comment
Create account
Create an account on our community. It's easy!
Log in
Already have an account? Log in here.