part 2 of 2 The use of tests is borrowing an uncertainty yardstick from sampling uncertainty and applying it to nonsampling sampling uncertainty. "The difference is (is not) consistent with the degree of uncertainty to be expected if it were due to sampling."
There is a change in the observed results the question is whether there is a difference in the actual phenomenon under consideration. Hope this helps. Art [EMAIL PROTECTED] Social Research Consultants University Park, MD USA (301) 864-5570 . . ================================================================= Instructions for joining and leaving this list, remarks about the problem of INAPPROPRIATE MESSAGES, and archives are available at: . http://jse.stat.ncsu.edu/ . =================================================================
