Nate Silver writes The Tilt in the NYT, parsing polling, Nate is not a pollster, he’s a journalist (and a professional poker player) writing about polls. Polls vary from pollster to pollster, a week away from election day The Tilt, sort of, without confidence, predicts a Trump victory,
In an election where the seven battleground states are all polling within a percentage point or two, 50-50 is the only responsible forecast. Since the debate between Kamala Harris and Donald Trump, that is more or less exactly where my model has had it.
Yet when I deliver this unsatisfying news, I inevitably get a question: “C’mon, Nate, what’s your gut say?”
So OK, I’ll tell you. My gut says Donald Trump. And my guess is that it is true for many anxious Democrats.
But I don’t think you should put any value whatsoever on anyone’s gut — including mine. Instead, you should resign yourself to the fact that a 50-50 forecast really does mean 50-50. And you should be open to the possibility that those forecasts are wrong, and that could be the case equally in the direction of Mr. Trump or Ms. Harris.
And to further confuse us Nate opines,
It is extremely hard to predict the direction of polling errors ….A surprise in polling that underestimates Ms. Harris isn’t necessarily less likely than one for Mr. Trump. On average, polls miss by three or four points. If Ms. Harris does that, she will win by the largest margin in both the popular vote and the Electoral College since Mr. Obama in 2008.
A poll is a photograph of likely voters at a particular time and the poll is designed to predict the general voting population, within a margin of error. If you average the major polls, some have Harris leading, others Trump, the polling is a statistical tie,
The key to polling is to identify likely voters and create a stratified, random sample, a microcosm of all voters.
* Who are likely voters (voted in the last two presidential elections)?
* How many subgroups? (gender, age, education level, race, income)
* Response rate (% responding to pollsters)
And the unanswerable questions that can skew polling results; for example:
How has the overturning of Roe impacted women? Has the decision increased the turnout of women? To what extent? Are these previous Trump or Harris voters? Previous non voters to voters? Trump voters to Harris voters?
And the same for new voters, has the number of new voters increased? Trump or Harris voters?
Are the polls “accurate”?
I predict the Harris women vote will be a tsunami, as well as the new voters.
Maybe I live in a bubble of smart women, I can’t remember any election that generated so much anger in a subgroup, namely women.
Last week I sat in on a few classes at a university I attended, one class was “The Rise of Nazism 1930-33,” and the instructor handed out the program of the Nazi party, eerily similar to the Heritage Foundation Project 2025.
Ed in the Apple: Blogging on the Intersection of Education and Politics Title 