I've gotten several emails and seen several postings about the NYTimes interview with Yale economist Ray Fair. Fair uses econometrics--statistics--to analyze various phenomena such as presidential elections. His model predicts that Bush will win 57.5% of the two-party vote in this year's election. For what it's worth (probably not much), I think that strong a showing by Bush is highly unlikely and that comparing the actual results to the Fair model's prediction will give us a nice example of the hazards of out-of-sample forecasting.

But, as my colleague Wilson Mixon points out about the interview, "The questions are more interesting than the answers." Consider this doozy (comment in [ ] is mine):

Q. It saddens me that you teach this [econometric analysis] to students at Yale, who could be thinking about society in complex and meaningful ways.

Ask any student who has studied it--econometrics is complex. And, at least if well done, econometrics can be meaningful. It's hard to think of things that are more meaningful than questions about how factors such as economic growth and unemployment affect people's voting decisions. Here are some people who know firsthand how meaningful such factors can be: Presidents Reagan and Clinton (who were elected to second terms) or Presidents GHW Bush and Carter (who were not).

Apparently the interviewer doesn't think honest scholarship is possible even if it goes against one's personal preferences. Consider this exchange:

Q. I don't want to do game theory. I just want to know if you are a Kerry supporter.

Q. I believe you entirely, although I'm a little surprised, because your predictions implicitly lend support to Bush.

What does this say about the corruption of the academy?