On Nate Silver….


I wasn’t planning to write about Nate Silver, but I keep reading articles about him and being asked about him. As this election has started to wind down, it’s strange how much significance his opinion seems to have taken on. I say it’s strange because Nate Silver is certainly a smart guy who did a good job of calling the 2008 election, but there are a lot of smart guys who do a good job of calling elections.

I don’t know why anyone would consider Nate Silver to be more likely to call ths election correctly than say Sean Trende, Jay Cost, Larry Sabato, Michael Barone, Charlie Cook, Stuart Rothenberg or Scott Rasmussen. Once you get beyond that group of professional statistics junkies, there’s probably another group of 30-40 bloggers, commentators, talk show hosts and columnists (along with many, many more behind-the-scenes pollsters and political operatives) who understand polling and elections well enough to conceivably outperform any of those guys in any given election.

That’s because national elections are massive undertakings with a lot of variables and often, there are minimal numbers of data points to work with, many of which tend to be unreliable. Under those circumstances, there is not any “master formula” that can be devised to reliably determine probabilities the way some people, including Nate Silver, were able to do with baseball. In baseball, there are an almost infinite number of clearly definable data points to work with. When it comes to America’s pastime, you may potentially be able to sift through decades’ worth of full seasons to create a model — while in politics, you may have to try to piece together what’s going on in a state like Michigan based on three recent polls done by 5th rate pollsters who do mediocre work.

With that in mind, you may say, “Well then, how can Nate Silver say with any sort of certainty that there’s a 77.4% chance that Obama will win the election?”

The honest answer is that he can’t.

Putting a number out like that with the incredibly limited amount of data we have to work with is nothing more than a gimmick. From Silver’s perspective, it may be a useful gimmick for the moment because it’s helping to set him apart from his peers, but unless he’s being fed internal polls by campaigns, he doesn’t special knowledge that would enable him to call this election with a level of certainly beyond that of the other people listed above.

Just read this excerpt from his latest post and you’ll see what I mean.

There have been other years like 1992 in which the national polls did a bit better. But on average since that year, the state polls have had a bias of 1.1 percentage points – half as much as the national polls, which have had a 2.1-point bias instead.

We’re approaching the point where Mr. Romney may need the state polls to be systematically biased against him in order to win the Electoral College. And that certainly could turn out to be the case: if Mr. Romney wins the popular vote by more than about two percentage points, for example, he’ll be very likely to cobble together a winning electoral map, somehow and some way. (And he’ll be a virtual lock if the results are in line with Mr. Romney’s best national polls, like the Gallup survey, which put him four or five points ahead.)

But the historical evidence weighs in slightly more heavily on behalf of the state polls, in my view, when they seem to contradict the national ones. If the state polls are right, than Mr. Obama is not just the favorite in the Electoral College but probably also in the popular vote.

Tuesday’s Polls

Mr. Obama made gains in the FiveThirtyEight forecast on Tuesday, with his chances of winning the Electoral College increasing to 77.4 percent.

That’s not an explanation of a master system, that’s someone noting, like most everyone else in the know, that the polling numbers aren’t matching up as they should and like everyone else, Silver is taking a guess as to why that’s the case. Sean Trende did the same thing yesterday. So did I.

In the end, maybe Nate Silver will turn out to be right, maybe Sean Trende will, or maybe I will. The truth is that all of us are waiting for Tuesday to see whose theory turns out to be validated and the one thing I can absolutely assure you of, is that nobody can tell you in any meaningful sense that he’s 77.4% certain that he’s right.

Also see...

Related Articles

7

Liberals So Stressed By Election That They Can’t Exercise Or Sleep

Funny stuff, via Mary Katherine Hamm (San Fran Chronicle) There’s no shortage of their kind in the politically bluest parts

3

Dear GOP, Let’s Not Waste Romney’s VP Pick on One of Our Best Guys, OK?

I don’t want Paul Ryan to be Romney’s Vice Presidential pick. I also don’t want Bobby Jindal, Chris Christie, or

50

Mitt Romney’s Foreign Policy Won’t Include “Frenemies”

We’re starting to get a glimpse of how a President Romney would act on the international stage, which would be