Econometrics Quote of the Day
15 October 2010 at 9:39 am Peter G. Klein 8 comments
| Peter Klein |
When I read empirical papers, I see many demonstrations of the IQ levels of economists, but I see the study of very few genuine empirical issues. I hardly see any intellectual capital at risk. As a result, I think we have much less progress as a science than we would if we made a serious effort to identify clearly some real issues.
That’s an Ed Leamer classic from 1988. The source is here. Related: “Puzzles or Problems?”
Entry filed under: - Klein -, Methods/Methodology/Theory of Science.
Organizations and Markets 
1.
Warren Miller | 15 October 2010 at 10:03 am
As a predictive science, econometrics ranks right up there with astrology.
2.
Rafe | 15 October 2010 at 2:54 pm
Don’t knock astrology by association.
Astrological predictions are usually more interesting.
3.
David Hoopes | 15 October 2010 at 4:29 pm
Leamer is great.
4.
Peter | 16 October 2010 at 2:59 am
So what are the real problems? How would it be possible to enhance the quality of economic research?
5.
Randy | 16 October 2010 at 6:51 am
Enhancing economics research would require abandoning econometrics; that is, finding an alternative to historical analysis.
6.
Peter Klein | 16 October 2010 at 7:28 am
@Peter: you gotta read the paper. Leamer is of course not an econometrics denier, but an econometrics reformer. See also his “Let’s Take the ‘Con’ Out of” paper.
7.
Dick Langlois | 16 October 2010 at 8:08 am
You may be surprised to hear me say this, but I think the Leamer quote is outdated. As I have believed for some time, mainstream economics today is almost entirely applied statistics — think Freakonomics. As Meir Kohn pointed out (2004, p. 306), this is largely because Arrow-Samuelson theory reached a dead end. (http://www.cato.org/pubs/journal/cj24n3/cj24n3-8.pdf) I think increasing computer power may have had something to do with it as well. A lot of this applied statistics
is quite good — better, for example, than the statistical stuff in management or even public health. Consider David Cutler on health, for example. In my view, economists are asking good statistical questions . Moreover, in my view, this is a much safer thing for 95 per cent of the profession to be doing than theorizing.
8.
Warren Miller | 16 October 2010 at 10:24 am
“Moreover, in my view, this is a much safer thing for 95 per cent of the profession to be doing than theorizing” – Dick, that’s MasterCard-ad priceless. I hate it when unsupervised economists-children get the matches out and burn the house down while the parents are elsewhere.
As for economists “asking good statistical questions,” I guess a lay person in 2010 might respond, “Yeah, but are they asking good policy questions?” Given the economic wreckage for which Democrats appear to be en route to severe punishment on Nov. 2, what’s your view about good statistical questions vs. good policy questions?