Much as I admire Steven Levitt, I hated
his meretricious book, Freakonomics, and I’ve made a conscious decision not
to put the Freakonomics blog in my blogroll. The huge success of the book, however,
has meant that a lot of other social scientists have tried to replicate its
success by using pseudo-provocative headings such as "What Bill Gates and
Paul McCartney have in common with criminals".
I haven’t read recent efforts along those lines by Tyler Cowen
or Tim Harford or Steven Landsburg, so I won’t
say anything about them. And I haven’t read Why Beautiful People Have More
Daughters by Satoshi Kanazawa, either, an excerpt
from which includes that bit about Paul McCartney. What I have read is an utterly
compelling take-down
of Kanazawa’s methodology by Andrew Gelman of Columbia
University.
Gelman is conflicted
about the book, and about Kanazawa’s work in general:
I just don’t know how to think about this. It’s clear to me how journalists,
bloggers, and reviewers should react: the should discuss this work with skepticism.
The trouble is that the papers were published in a reputable journal (J. Theor.
Biology), and a journalist/blogger/reviewer who does not happen to see my
critique would naturally tend to trust the result…
Should I blame Kanazawa? I don’t want to be dismissive of scientific speculation–I
don’t like the idea of statistican as censor–so maybe there would be a way
for him to present more of the full
statistical story in his book (for example, in the beauty-and-daughters
study, a graph with the proportion of girls born to people of all five beauty
categories–rather than just comparing categories 1-4 to category 5–along
with the beauty assessments from all three waves of the study). It’s a tough
call to decide how to present speculative findings.
I think Gelman is being far too easy on Kanazawa here. The book, especially,
has nothing to do with presenting speculative findings, and everything to do
with trying to hit a Freakonomics-style home run in the publishing world. This
isn’t science, it’s business. And if a book like this can sell more copies by
fudging the science, there’s a good chance that it will. That’s basic economics,
that is.