I' not completely sure what you mean.
You could apply your subjective criteria to the standardized residuals or standardized predicteds. (If you are using SPSS see the syntax documentation on the /RESIDUALS specification. If you want to recode into a larger number of categories, you might consider polychotomous ordered logistic regression (e.g., PLUM in SPSS). bad high, ok, bad low. 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/ . =================================================================
