"John Uebersax" <[EMAIL PROTECTED]> wrote in message news:[EMAIL PROTECTED] > Stan's problem is very interesting. I believe it points to a more basic > paradox concerning Laplace's "principle of indifference." ......... see his post above.... > "Choose from a set of otherwise equivalent models of a given phenomenon > the simplest one" [but who decides when models are 'otherwise equivalent' > and who decides which is 'simplest'?] ............................. These ideas that John points out here are absolutely fundamental.
Along the same line... Fisher's equiprobable sample, which is the basis for using sampling/population distributions to come to some conclusions. How do we determine "equi-probable"? By opinion of the most learned expert? If the p value suggests a rejection of the simplest model, is it because of the logical weakness of the hypothesis, or is because a more complicated model is a better approximation to reality? This is the fundamental problem in SEMNET, on determining whether a given Structural Equation fits or does not fit a set of data and theory. David Heiser . . ================================================================= Instructions for joining and leaving this list, remarks about the problem of INAPPROPRIATE MESSAGES, and archives are available at: . http://jse.stat.ncsu.edu/ . =================================================================
