Nate Silver trashed his former website in a Vanity Fair interview saying the FiveThirtyEight model is “broken” and added: “I don’t think you can trust anything from that forecaster.”

Rick Perlstein: “In 2016, I experienced the desolation of my candidate for president losing after the most respected polling experts told me she had a 71.4 percent, 85 percent, 98.2 percent, and even 99 percent chance of winning. As a historian, I was studying how Ronald Reagan’s runaway landslide in 1980 was proceeded by every pollster but one supremely confident that the race was just about tied.”

“I’ve just finished a fine book published in 2020 that confirms an intuition I’ve been chewing on since then. It turns out this is practically the historical norm. W. Joseph Campbell’s Lost in a Gallup: Polling Failure in U.S. Presidential Elections demonstrates—for the first time, strangely enough, given the robust persuasiveness of its conclusions—that presidential polls are almost always wrong, consistently, in deeply patterned ways.”

Dan Pfeiffer: “Riding the pollercoaster is an exercise in insanity. A few things to keep in mind (I like to reiterate these reminders every month or so): first, polling is an inexact science. There is a margin for error. A poll that shows Harris up two and one that shows her down two are essentially the same.”

“Second — and I can’t emphasize this enough — polling is not supposed to predict the future. It tells us our present. Let’s say the NYT poll is right. Harris is down two in North Carolina now, but has more than a month to make up that gap. Finally, it is totally okay to ignore all of the polls, but if you must look,  focus on the averages. They smooth out the statistical variance inherent in individual polls.”

Natalie Jackson: “Forecasts based on polls and election ‘fundamentals,’ like what FiveThirtyEight, The Economist, and Nate Silver produce, are more intriguing from an empirical standpoint. The statistical machinations are genuinely challenging and interesting to work on: combining national and state-level polls, economic factors, incumbency factors, and vote history, and then spinning it all up into a state-by-state prediction that can be used to simulate presidential elections. We’re talking thousands and thousands of lines of code.”

“Sounds pretty empirical, right? It is, in the sense that you build a big model that takes in a ton of data and puts out a ton of data. But every decision about what goes into the model is subjective: The modeler decides what polls are used, whether they are adjusted for the quality or past accuracy of the pollster, how much any individual poll is able to move the trend, which economic indicators to use, which political factors are important, and how all those are coded in. Make a different decision at any step, and you change the model’s predictions…”

“We can calculate probabilities all day long, but we have no idea what their accuracy is. Polls have margins of error, plus additional error. Models have error of their own. Judgment calls made by those constructing the models have error. We don’t know how big all of that cumulative error is.”

Patrick Ruffini: “The point here is not that the polls are fake or that respondents are lying. Polls are a reflection of the political moment when the poll is taken. And merely asking a hypothetical can’t begin to approximate the dynamics of a change once it actually takes place.”

“Especially as July wore on, some polls were directionally right about Harris polling better than Biden. But these polls got the psychology of the electorate wrong, suggesting a replacement would fare almost as badly as Biden, with all of the downsides Flaherty outlined in his memo.”

“What polls didn’t capture was the enormous sense of relief that would wash over the Democratic Party once the Biden drama was resolved, leading at least for now to a consolidation of the party’s base behind Harris. Three weeks ago, the party was anything but unified, so the polls taken at the time, with their dejected and despondent Democratic samples, weren’t that helpful in making the case for a switch.”

Derivative Polling tracks changes in polls from the same pollster.

“Rather than combining every poll under the sun, with complex corrections for pollster reliability, bias, state effects, economic fundamentals or whatnot, this tracker instead focusses on changes from one poll to the next by the same pollster.“

It’s updated daily.

“Candidates and voters alike are wondering whether they can trust the polls ahead of November’s elections,” Axios reports.

“The 2016 and 2020 elections rocked public confidence in polling after many underestimated the amount of support for former President Trump. Meanwhile, pollsters are having to adapt their methods, with fewer respondents answering the phone.”

Nate Silver has released new pollster ratings which differ from the methodology used by his old home, FiveThirtyEight.

“The top-rated pollsters — Selzer & Co. and The New York Times/Siena College — will be familiar to longtime readers.”

“For the record, though, eligible polls in the 2024 presidential primaries missed the final margin between the top two candidates by an average of 9.7 percentage points. That isn’t very accurate, obviously — but it’s consistent with the long-term average error in presidential primary polls since 2000, which is 9.3 percentage points.”