Saturday, November 22, 2003

I haven't gone back to Steven Jay Gould (Nov 16) yet. I've been too busy for real thought. In the meantime I had hoped to link to this article on Amartya Sen in the new issue, but now I see you have to pay for it. Again, from the Gould article:

Linda is active in the feminist movement;
Linda is a bank teller;
Linda is a bank teller and is active in the feminist movement.

Now it simply must be true that the third statement is least likely, since any conjunction has to be less probable than either of its parts considered separately. Everybody can understand this when the principle is explained explicitly and patiently. But all groups of subjects, sophisticated students who ought to understand logic and probability as well as folks off the street corner, rank the last statement as more probable than the second. (I am particularly fond of this example because I know that the third statement is least probable, yet a little homunculus in my head continues to jump up and down, shouting at me—"but she can't just be a bank teller; read the description.")


Obviously, my point is that I think we 'match to type' for a reason, and that 'type', or belief, skews statistical analysis.
Imagine a description of Linda that implies, but does not state, that she is Jewish (call it racial profiling.)
Then attach these options:

Linda is an FBI agent;
Linda is a member of the American Nazi Party;
Linda is an FBI agent and a member of the American Nazi Party.
---

Politics: Today?
I'm disgusted. We'll leave it at that for now. It's a beautiful afternoon,
I'm going outside to play.

No comments: