Recent Blog Posts
-
The Times' Rorshach Geithner Story
Apr 27 20099:04am EDT -
Sinking Animal Spirits
Apr 27 20098:04am EDT -
Counter-cyclical Urban Policy
Apr 26 200910:04am EDT -
Be Your Own Counterfeiter
Apr 26 20099:04am EDT -
Being Tim Geithner
Apr 25 200912:04pm EDT -
Notes From a Press Conference Naif
Apr 25 20099:04am EDT -
What Good is the News?
Apr 25 20098:04am EDT -
Stressful Enough
Apr 24 20092:04pm EDT -
Not Regretting the Pound
Apr 24 20091:04pm EDT -
Introducing the New Ford Squeeze
Apr 24 20099:04am EDT -
Non-Economic Questions of the Day
Apr 24 20099:04am EDT -
The Stress Test Blind Alley
Apr 24 20098:04am EDT -
Happy Hour
Apr 23 20099:04pm EDT -
Recovery Without Rebalancing
Apr 23 20096:04pm EDT -
The Shape of Your Recession
Apr 23 20095:04pm EDT
Links
- Felix Salmon

- DealBreaker

- Ryan Avent: The Bellows

- The Epicurean Dealmaker

- Chris Anderson

- Ultimi Barbarorum

- MarketBeat

- Michelle Leder

- John Quiggin

- The Panelist

- Andrew Leonard

- Streetsblog

- Brad Setser

- Michael Mandel

- Financial Crookery

- Kash Mansori

- Dean Baker

- Calculated Risk

- Free Exchange

- Curbed

- Lance Knobel

- Econospeak

- Carbon Tax Center

- Overcoming Bias

- Mark Thoma

- Naked Capitalism

- Alphaville

- Barry Ritholtz

- Alexander Campbell

- The Bayesian Heresy

- Brad DeLong

- DealBook

- Greg Mankiw

- Deal Journal

- FP Passport

- Carl Bialik

- Marginal Revolution

- A Fistful of Euros

- Dan Gross

The Limits of Empiricism, Revisited
Deirdre McCloskey is in fine fighting form, at least by the standards of statisticians:
Good fit is not the same thing as importance. In fact, usually it has nothing to do with importance.
I think she's absolutely right. People who use a lot of statistical analysis, economists among them, tend to gravitate towards the measurable. Often, important things aren't easy to measure, and things which are easy to measure aren't important. While statistical analysis should be used to examine some a priori hypothesis, too often hypotheses are constructed around whatever data might be lying around. And if the data is crap, the results of any statistical analysis on that data will also be crap, no matter how good your fit.
(Earlier: The Limits of Empiricism)






