Slashdot Mirror
All of Nate Silver's State-Level Polling Predictions Proved True
kkleiner writes "For the last few months, the political pundit class has been at war with NYT/FiveThirtyEight blogger Nate Silver. Joe Scarborough of MSNBC called him a "joke," while an op-ed in the LA Times accused him of running a "numbers racket." But last night, Silver triumphed: every one of his state-level presidential predictions proved true. "
...that's not how statistics work either. A result does not alter the underlying probabilities.
I've always found the best way to find great news sources is to hold them accountable and stop using them when they screw up the big stories. For example, when the media was shocked by the 2008 crash, I wasn't. I had predicted it 5 years earlier (not necessarily when, but the fact that it would happen). How? I took a look at the small handful of pundits and bloggers that accurately predicted the demise of the tech bubble and looked at what they said would be the next bubble. If people actually started paying attention to the sources that get it right, vs the ones with the largest reach, places like FOX wouldn't exist. What I have found over the past decade is that far left independent news sources get it right far more often than mainstream (or far right) new sources.
The election is another great example. Some people weren't surprised, and those are the ones that we should look to next time, unless we enjoy being a bunch of dumbfounded idiots all the time.
but for instance, we had no way of knowing if a "Bradley Effect" would have been in play
Sure we do. Nate Silver has looked at this effect a number of times. If it exists at all, it's tiny.
http://www.fivethirtyeight.com/search/label/bradley%20effect
I'm not saying that the probability of systematic error is large, just unknowable.
It is knowable, and that's exactly why Nate Silvers forecasts are so much more accurate than anyone else's. He does the donkey work to minimise these systematic errors.
It was a perfectly reasonable and scientific position for a Republican to say "Romney's chances are equal to the probability of error in the polls, and I hope that probability is large."
No, it was really, really dumb. Not only can systematic errors be minimised, but margin of error is not going to go in the same direction on all polls.