Ah, Nate Silver, the new boyfriend of the chattering class. Everyone wants a piece of him and his methodology. We know he’s constantly surrounded by models, but would he like to be surrounded by a different kind of model? He should be warned, though: We might be skewed.
“Say methodology again,” Twitter breathes. “Slower. Now turn. That’s right. Now tell us we’re beautiful, but using probability.”
He’s earned this, correctly predicting the winner of 50 of 50 states this election, using a model that combines Bayesian probability with polling data. Inspired by his commitment to data, here are some facts about Nate Silver that the Internet just made up. I hope this is how data works.
These, from Twitter, are about 90.9 percent probable — at least in the Nate Silver sense that if, they turn out to be wrong, you would need to run the model hundreds more times to be sure.
— “Results ask Nate Silver if they’re significant.” — @collision
— “Nate Silver's samples have only a median and a mode. Because no number would be mean to Nate Silver.” — @dilefante
— “Nate Silver can recite pi. Backwards.” -@smedette
— “When Nate Silver goes out to eat, his tips alway accurately correspond to the quality of the service.” — @benhuh
— “When Nate Silver asks you, ‘Wanna make a bet?’ the correct answer is no.” — @perko
— “There are no imaginary numbers, only ones Nate Silver hasn't acknowledged yet.” — @tbq_
— “Nate Silver can divide by zero.” — @jkfecke
There’s plenty more in the Twitter hashtag where these came from!