A Qlog

I'm not sure that democracy works for programming language design.

For a long time, I have thought I was a statistician... All in all, I have come to feel that my central interest is in data analysis...

Getting information from a table is like extracting sunbeams from a cucumber.

Survey weights are like McDonald’s chicken nuggets—you don’t know what goes into them.

In statistics it’s enough for our results to be cool. In psychology they’re supposed to be correct. In economics they’re supposed to be correct and consistent with your ideology.

We who are liberal and progressive know that the poor are our equals in every sense except that of being equal to us.

But if a profit occurs—at any rate, if the profit does not come from political favors, as it does to the sugar industry or the wind-farm industry—the economy is articulating something worth attending to. It is saying, 'Do more of this. People want it strongly enough to pay for it.' If a loss occurs it is saying, 'Don’t do that. People won’t pay for it.' The articulation comes from the dollar votes of ordinary people, a democracy of what people in aggregate are willing to pay.

If an economist is making, say, a calculation of purchasing power parity between South Africa and the United States over the past century, she would not be much troubled by a failure of fit of, say, plus or minus 8 percent. If her purpose were merely to show that prices corrected for exchange rates do move roughly together and that therefore a country-by-country macroeconomics of inflation would be misleading for many purposes, such a crude level of accuracy does the job. Maybe plus or minus 20 percent would do it. But someone arbitraging between the dollar and the rand over the next month would not be so tranquil if his prediction were off by as little as 1 percent, maybe by as little as 1/10 of 1 percent, especially if he were leveraged and unhedged and had staked his entire net wealth on the matter.

Pigovian taxes are not going to get the right solution, except by happy accident.

'[A]n item gravitates by exchange into the hands of the person who values it the most, if transactions costs are not too high.

we study the same models of the market and the price system as they do at Chicago, but at Chicago, they believe the models, where at Harvard/MIT we don’t.

We curtsy to Marshall but we walk with Walras

To know anything, one most know everything

Formal statistics is not a substitute for either thinking or working.

Statistical techniques do not solve any of the common-sense difficulties about making causal inference.

If you only do what you can do, you'll never be more than you are now.

Nowadays, if you give up looking for a job, it's like they consider you employed