Thursday, February 12, 2009

a perhaps more fitting tribute to Darwin

A former colleague sent me this link from ScienceNews:
Darwin: The reluctant mathematician
Despite disliking mathematics, the great biologist inadvertently advanced statistics
The article tells the story of Darwin's genetic experiments on a wildflower, Common Toadflax. (note: this was pre-Mendel, and the word "genetics" would have been foreign to Darwin.)

Trying to determine if cross-breeding produced superior plants compared to in-breeding, Darwin reasoned out a particular experimental design now known as a paired-comparison - a simple version of blocking.
(Note: these experimental efforts were motivated by logical inferences from Darwin's theory of natural selection - yes, his theory implied directly testable hypotheses!)

Darwin not having the mathematical expertise to fully analyze his data presented the problem to his cousin, Francis Galton, a pioneer in the field of statistics.
(Note: though Darwin's cross-bred plants were on average more robust than the in-bred, Darwin recognized that variation within populations made it troublesome to draw firm conclusions based on averages alone. It was this problem that motivated him to seek assistance from Galton.)

Galton could help some, but not enough to provide quantifiably phrased conclusions.

There the matter rested for a number of years, till a fellow at the Guinness Brewery - Wm. S. Gosset - attacked the problem. Publishing under the pseudonym "Student", Gosset provided the mathematical framework within which to compute a quantitative conclusion.

R.A. Fisher took up the challenge a few years later.
As a college student, Sir Ronald Aylmer Fisher learned about Gregor Mendel’s work in genetics and Darwin’s work in evolution, but the theory connecting the two hadn’t yet been developed. Fisher set out to create the statistical foundation to make the connection possible. Darwin’s experiment with hybrids was just the kind of problem Fisher needed to be able to solve.

He noticed something that Galton had missed: Galton had ignored Darwin’s clever method of pairing the plants.
...
Fisher’s analysis was only possible because Darwin had designed his experiment so well. In fact, Fisher was often frustrated with the quality of other people’s experiments. “To call in the statistician after the experiment is done,” he said, “may be no more than asking him to perform a postmortem examination: he may be able to say what the experiment died of.”
The verdict of a modern-day statistician seems an appropriate coda:
David Brillinger, a statistician at the University of California, Berkeley, says that Darwin’s method of pairing is now common practice. “Darwin was a leader in a subfield of statistics called experimental design,” he says. “He knew how to design a good experiment, but what to do with the numbers was something else."
Again: Happy Birthday, Charles!

No comments:

Post a Comment