Semi-Daily Journal Archive

The Blogspot archive of the weblog of J. Bradford DeLong, Professor of Economics and Chair of the PEIS major at U.C. Berkeley, a Research Associate of the National Bureau of Economic Research, and former Deputy Assistant Secretary of the U.S. Treasury.

Sunday, November 12, 2006

I Have to Disqualify Donald Luskin from the Stupidest Men Alive Contest

An unarmed man in a contest of wits. A correspondent emails me that National Review's Donald Luskin is puzzled because he cannot reproduce Paul Hacker's findings of rising income instability in America:

The Conspiracy to Keep You Poor and Stupid: Yale economist [sic: he is a political scientist] Jacob Hacker has been getting a lot of play in the mainstream media with his new book The Great Risk Shift -- a kind of Bush-bashing self-help book.... Hacker's thesis, in a nutshell, is that... people don't feel "economic security." His seemingly scientific proof statement is a chart of what he calls "income instability."...

I can't find any other data series that even remotely gives me this result... three that I calculated... [per capita disposable income, median households income, average hourly earnings].... All three are different measures of the volatility of income -- and none of them look the slightest like Hacker's... they lead one to the opposite conclusion -- that incomes have become less unstable through time....

One has to wonder just how Hacker tortured his data to get it to confess that incomes are more unstable today then [sic: than] they've been in the past.

Luskin's confusion can be easily cleared up. Hacker calculates the average variability of individual Americans' incomes. Luskin calculates the variability of the average of individual Americans' incomes. As everybody who has taken even one semester of statistics--or even thought about it for fifteen minutes--knows: in general the variability of the average is not equal to the average of the variabilities. Why on earth should anybody think it should be?

For Luskin to claim that there must be something wrong with Hacker's numbers because Hacker's calculations of the average variability don't line up with Luskin's calculations of the variability of the average, well...

There is a reason I have to disqualify Donald Luskin from this year's Stupidest Men Alive contest: He's a ringer. It just wouldn't be fair to the other contestants.

0 Comments:

Post a Comment

<< Home