Thread by @NateSilver538

So... this is a special morning for our forecast in that there's now no more time until the election. (The model treats Election Day and Election Eve as equivalent to one another.) This has a couple of minor effects.

projects.fivethirtyeight.com/2020-election-…

1. The forecast is now totally polls-based; there's no longer any prior for economics/incumbency. The weight assigned to this prior had been declining anyway so that it was close to zero, but now it's actually zero.

2. One type of uncertainty—"drift", or how much polls change between the present day and the election—is also now gone. Of course, there's still the chance that polls could be *wrong*. But there's no longer time for polls to change (though a few more will straggle in today.)

The factors (reducing the amount of uncertainty and reducing the weight assigned to the prior, which expected the race to tighten) had gradually been helping Biden. They're why his win % had been drifting upward even while the polls were basically flat or tightening by a hair.

Biden got a tiny further boost this morning (from 89% to 90%*) from this plus some decent polling for him. But now there are no longer any further gains to be had for Biden from the mere passage of time.

* Yes, just over the "clearly favored" line in our verbiage

Bottom line: our final forecast is likely to be very close to what you see now (i.e. 90/10 or thereabouts). Could it be 92/8 or 88/12? Sure. But there's so much polling in most of these states now that new polls aren't shifting things much.

Nor is there anything magical that will happen when we run the final model just after midnight.

And hey, pollsters: Please do get those polls to us by midnight! We expecting that to be our final run of the season.