Thursday, March 27, 2014

Silver vs. Krugman

I have been a real fan of Nate Silver's work, but this is totally absurd. It's like a parody of Silver's data crunching. His theory seems to be that Paul Krugman is part of a New York Times cabal, the cabal is pissed off at Silver for taking his 538 site away from the times, and is now retaliating against him by saying mean things about his work on the internet. None of that deals with the substance of Krugman's criticism, which is:

Unfortunately, Silver seems to have taken the wrong lesson from his election-forecasting success. In that case, he pitted his statistical approach against campaign-narrative pundits, who turned out to know approximately nothing. What he seems to have concluded is that there are no experts anywhere, that a smart data analyst can and should ignore all that.

But not all fields are like that — in fact, even political analysis isn’t like that, if you talk to political scientists instead of political reporters. So, for example, before glancing at some correlation and asserting causation, you really should talk to the researchers.

Silver responds by going through Krugman's archives for references to "Nate Silver"  semi-arbitrarily labeling each reference as "favorable," "unfavorable," and "neutral.," and then showing that things have turned mostly unfavorable since ESPN became the host for 538. But how does that address Krugman's point? In fact, he seems to be doing exactly what Krugman was accusing him of. As Krugman said, "data never tell a story on their own. They need to be viewed through the lens of some kind of model, and it’s very important to do your best to get a good model." In this case, Silver's attempt to quantify Krugman's attitudes does nothing to deal with the substance of Krugman's criticism.

I don't know why Silver feels like he has to get into a petty tit-for-tat exchange with Krugman. (The best rebuttal would have just been doing good work.) And I don't know why he thought his latest tat was an actual response to any of Krugman's criticisms.

(via Memeorandum)