Watching the right wing rage at Nate Silver is kind of amusing to watch. Andrew Sullivan points out that Silver’s predictions on the results of the election are quite in line with all the other major poll analysts and betting markets, while Jonathan Last tries to explain how probability works:
If Romney wins should that discredit Silver’s models? Only so far as anybody ever used them as oracular constructs instead of analytical tools.
One final word: People seem to think that it would reflect badly on Silver if Romney were to win while Silver’s model shows only a 25 percent chance of victory. But isn’t 25 percent kind of a lot? If I told you there was a 1-in-4 chance of you getting hit by a bus tomorrow, would you think that 25 percent seemed like a big number or a little number? Or, to put it another way, a .250 hitter gets on base once a game, so you’d never look at him in any given at bat and think there was no chance he’d get a hit.
This is something that any decent poker player knows, of course. Take the hand I wrote about the other day from the World Series of Poker, where one player had a pair of kings and the other had an ace and a king. They got all the money in before the flop and at that point the player with the kings was approximately a 70/30 favorite to win the hand. That means three times out of ten, the underdog is going to win. If you bat .300 in baseball, you’re probably in the hall of fame. And in that case, the underdog did win. And even prior to the very last card, he still had about a 15% chance of winning (he could hit any one of seven cards to win — the three remaining aces or the four remaining 4s; each “out” in poker is worth about 2.1% per card to come).
So no, if Romney wins that won’t prove Silver, or any of the other statistical analysts handicapping the election, wrong. But I’d be willing to bet that if you look at his national and state by state predictions, he’ll be pretty close. Why would I be willing to bet that? Because I understand probability.