On Tue, 7 Oct 2003, BELIS Marianne wrote:

}example of the raincoats for which you ask a "causal" solution. Indeed,
}the present theories don't seem to be very adequate to solve it. 

Ummm. What theories?  I thought causal models rather naturally handled
this stuff. They've been around since about 1920 (for linear models),
assigning degrees of causation, etc.  Granted, only recently have people
given them a good semantics for determining degree of responsibility
after-the-fact, but they have done so.

}competitor,improved styling, etc. On each of them we assign a weight in
}.... Then we calculate the summ of the weighted strenghts. 

Sounds like Sewall Wright's path models to me. Put a weight on each
arrow, and the resulting effect is the sum of the product of the values
times the weights. Apply chain rule for paths of length > 1.

-C

--
Charles R. Twardy, Res.Fellow,  Monash University, School of CSSE
ctwardy at alumni indiana edu   +61(3) 9905 5823 (w)  5146 (fax)

"Incongruous places often inspire anomalous stories." -- S.J. Gould

Reply via email to