FiveThirtyEight’s Nate Silver blasted the Huffington Post in a tweetstorm Saturday afternoon, after the website published a critical article accusing Silver of “monkeying around with the numbers” in his forecasting model.
Silver’s forecast has remained notably bullish on Donald Trump’s chances, a departure from many other poll aggregators that show more confidence in a victory for Democratic nominee Hillary Clinton.
As of Saturday, for instance, Silver’s model said Trump has a 35.2% chance of winning the election, whereas the Huffington Post’s model pegged his chances at 1.4%.
This, according to the Huffington Post’s Ryan Grim, is because Silver has been “putting his thumbs on the scale” and “making a mockery of the very forecasting industry that he popularized.”
FiveThirtyEight’s model uses “trend-line adjustment” in its forecasts, which compares different editions of polls and adjusts the results by using a regression analysis that draws a trend line.
"Silver is changing the results of polls to fit where he thinks the polls truly are, rather than simply entering the poll numbers into his model and crunching them," Grim wrote.
He also criticized Silver for whipping up panic, and added that readers of the left-leaning website could "relax" about Clinton's chances.
Silver immediately took to Twitter to slam Grim's article as "f---ing idiotic and irresponsible."
"This article made clear you have **no f---ing idea** what you're talking about. That's why you contract (sic) people **ahead of time**."
Silver went on to defend FiveThirtyEight's model as being based on empirical evidence, and criticized the HuffPost model as "not defensible."
Here's the rest of Silver's tweetstorm:
The reason we adjust polls for the national trend is because **that's what works best emperically**. It's not a subjective assumption.
— Nate Silver (@NateSilver538) November 5, 2016
Every model makes assumptions but we actually test ours based on the evidence. Some of the other models are barley even empirical.
— Nate Silver (@NateSilver538) November 5, 2016
If you haven't carefully tested how errors are correlated between states, for example, your model will be way overconfident.
— Nate Silver (@NateSilver538) November 5, 2016
There's a reasonable range of disagreement. But a model showing Clinton at 98% or 99% is not defensible based on the empirical evidence.
— Nate Silver (@NateSilver538) November 5, 2016
That's what makes a model a useful scientific & journalistic tool. It's a way to understand how elections work. Not just about the results.
— Nate Silver (@NateSilver538) November 5, 2016
The philosophy behind 538 is: Prove it. Doesn't mean we can't be wrong (we're wrong all the time). But prove it. Don't be lazy.
— Nate Silver (@NateSilver538) November 5, 2016