NP: John Cage, 4'33"

Nate Silver does a post-mortem on his Academy Award predictions. If you're into data analysis, this is by far my favorite bit:

Whenever we make an incorrect prediction, we are probably better off asking questions along these lines:

What, if anything, did the incorrect prediction reveal to us about the model's flaws? Was the model wrong for the wrong reasons? Or was it wrong for the right reasons? What, if any, improvements should we make to the model given these results?

Real modeling isn't entirely about being right or wrong, although that's certainly a big part of it. It's also about improving your understanding of what it is you're modeling. I think the political punditry (one of Silver's two bread-and-butter domains, along with baseball) gets really hung up on the first thing to the point where they're not attuned at all to the second.