Silver for the Gold

Silver Medal
Subtitle: Obama’s big win does not mean Nate Silver is a towering electoral genius.

It’s well after midnight on the East Coast, and the results are in: Nate Silver has won the 2012 presidential election by a landslide. His magic formula for predictions, much maligned in some corners in recent weeks, appears to have hit the mark in every state—a perfect 50 green M&Ms for accuracy. Now my Twitter feed is blowing up with announcements of his coronation as the Emperor of Math and the ruler of the punditocracy. Wait—it was even more than that, they say: a victory for blogging, and also one for rational thought. He proved the haters wrong! He proved science right! Is this guy getting lucky tonight or what?
But all these stats triumphalists have it wrong. Nate Silver didn’t nail it; the pollsters did. The vaunted Silver “picks”—the ones that scored a perfect record on Election Day—were derived from averaged state-wide data. According to the final tallies from FiveThirtyEight, Obama led by 1.3 points in Virginia, 3.6 in Ohio, 3.6 in Nevada, and 1.9 in Colorado. He won all those states, just like he won every other state in which he’d led in averaged, state-wide polls. That doesn’t mean that Silver’s magic model works. It means that polling works, assuming that its methodology is sound, and that it’s done repeatedly.

Two things: 1) yes, it does mean — to some degree of certainty — that Silver’s model works, and 2) you’re missing the point of the triumph. This wasn’t Nate Silver vs the pollsters, it was Nate Silver vs the pundits. And most of the pundits botched almost everything having to do with statistics beyond a trivial interpretation, and said that the predictions from the 538 blog were bogus. This was a triumph of statistics done right over the people who abuse, or are clueless about, statistics.

Put another way, the pundits had the same access to the polling data. And they were all over the place in their predictions, because they went with their gut instead of the data. That’s the underlying lesson.

The article points out, quite fairly, that other people use statistics properly, and had similar success in their predictions. Which raises the question — why all the other pundits weren’t doing this? The message here, if you hadn’t already figured it out, is that punditry is not about prediction, it’s about rabble-rousing and guesswork. Claiming that doing the electoral math is easy is a bit disingenuous when almost nobody who had a big platform (i.e. television) was doing it. It’s easy to see in hindsight, and apparently it’s easy to continue to try and marginalize the effort and the results.

Further, when you insist that predicting the result of the presidential race doesn’t prove he was right — with which I agree — you can’t then turn around and look at other individual races to say he was wrong.