The 2012 US election is today.

As of this morning Nate Silver of 538 is comfortably calling the election for Obama. Greater than a 90% chance of winning. That’s fairly comfortable right?

On the other hand Rasmussen is giving the election to Romney. 49% to 48%.

They can’t both be right, can then? Technically they could. The US electoral college system means that you can win the popular vote and lose the election. Ask Al Gore about what that feels like.

That aside, what we’re dealing with here are models, hypothesis and probabilities. Nate Silver is running one set of models over a set of data based on his hypothesis of what all the polling data is predicting. He had a pretty good record in 2008. Rasmussen is running another set of hypothesis over data that his polling firm is collecting. He had a pretty good set of predictions in 2008 as well.

It’s important to remember that its a prediction, not a fact. Silver himself points out that

Averaging polls together increases their sample size — making them much more powerful statistically than any one poll taken alone. But the errors in the polls are sometimes correlated, meaning there are years when most of them miss in the same direction. Mr. Romney remains close enough to Mr. Obama that he could fairly easily win the popular vote if there is such an error in Mr. Obama’s favor this year.

Similarly Rasmussen’s electoral college prediction calls it a toss-up.

It will be interesting tomorrow to look at what actually happens. What of Silver’s prediction of Romney’s 8% chance of winning the election if Romeny wins?

As any poker player knows, those 8 percent chances do come up once in a while. If it happens this year, then a lot of polling firms will have to re-examine their assumptions — and we will have to re-examine ours about how trustworthy the polls are. But the odds are that Mr. Obama will win another term.

It’s probable, based on the the evidence, that Obama will win. It’s not certain.  It’s going to be interesting to take a look at the different models after the election. You know, so we can start discussing Hillary 2016. :-)