how often and under what conditions ... might the AVERAGE deviation (AD) be larger for a set of data that has a SMALLER variance/sd (or reversed)? while not really looking at ADs very often, i have a two set set of data now ... that seems to be like that and, it looks strange Row sortver devver C20 sortmath devmath C21 1 719 113.533 113.533 719 77.4 77.4 2 693 87.533 87.533 719 77.4 77.4 3 662 56.533 56.533 710 68.4 68.4 4 655 49.533 49.533 701 59.4 59.4 5 648 42.533 42.533 701 59.4 59.4 6 646 40.533 40.533 700 58.4 58.4 7 643 37.533 37.533 693 51.4 51.4 8 623 17.533 17.533 665 23.4 23.4 9 613 7.533 7.533 643 1.4 1.4 10 585 -20.467 20.467 614 -27.6 27.6 11 585 -20.467 20.467 611 -30.6 30.6 12 580 -25.467 25.467 611 -30.6 30.6 13 571 -34.467 34.467 557 -84.6 84.6 14 454 -151.467 151.467 509 -132.6 132.6 15 405 -200.467 200.467 471 -170.6 170.6 MTB > desc c10 c11 Descriptive Statistics: sortver, sortmath Variable N Mean Median TrMean StDev SE Mean sortver 15 605.5 623.0 612.2 83.3 21.5 sortmath 15 641.6 665.0 648.8 78.7 20.3 Variable Minimum Maximum Q1 Q3 sortver 405.0 719.0 580.0 655.0 sortmath 471.0 719.0 611.0 701.0 MTB > sum c20 Sum of C20 Sum of C20 = 905.60 MTB > sum c21 Sum of C21 Sum of C21 = 953.20 MTB > _________________________________________________________ dennis roberts, educational psychology, penn state university 208 cedar, AC 8148632401, mailto:[EMAIL PROTECTED] http://roberts.ed.psu.edu/users/droberts/drober~1.htm ================================================================= Instructions for joining and leaving this list and remarks about the problem of INAPPROPRIATE MESSAGES are available at http://jse.stat.ncsu.edu/ =================================================================