Gus,
You are doing something that you wish me to affirm but you are not telling me what you are doing. Filling out the corners very definitely does have something to do with CR. The width of the intervals does as well. If you are creating intervals that have equal densities, then those intervals will be wider in the extremes and narrower in the midrange. This will make it look like the distribution is uniform but really it still has the disjunctive pairings in the extremes of x1 and x2 that characterize normal distributions. You are being evasive. Why will you not explain what you are doing? Bill "Gus Gassmann" <[EMAIL PROTECTED]> wrote in message [EMAIL PROTECTED]">news:[EMAIL PROTECTED]... > > > [EMAIL PROTECTED] wrote: > > > Gus, > > > > Does the procedure you use fill out the corners of a cross tabulation of x1 > > and x2? Are the intervals or equal width? > > Yes and yes, although neither has anything to do with the central question > I am asking you: > > > > I don't want to give the entire sample here, but let's say it looks like > > this: > > > > > > Row x1 x2 y > > > 1 0.47 0.15 0.62 > > > 2 0.71 0.43 1.14 > > > 3 0.77 0.87 1.64 > > > ... > > > 100 0.50 0.74 1.24 > > > > > > Now suppose I take a subsample from this, for instance, > > > I select rows 2, 7, 16, 33, 39, 54, 66, 71, 90, 99. > > > In this subsample, is y still caused by x1 and x2 or not? > > ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ > > IS IT? > . . ================================================================= Instructions for joining and leaving this list, remarks about the problem of INAPPROPRIATE MESSAGES, and archives are available at: . http://jse.stat.ncsu.edu/ . =================================================================
