JOM-e Logo The following is a supplement to the article "Extrusion Die Design: A New Methodology for Experimental Design as a Precursor to Neural Networks" by Bhavin V. Mehta et al., which is as part of JOM-e, 51 (9) (1999).

Table II. Data Analysis for Case 25-1
Average 1 2 3 4 Effect SS
(1) 0.2169 0.4066 4.4716 11.2679 22.4902 2.8113 ***
a 0.1897 4.0650 6.7962 11.2223 -1.0683 -0.1335 0.0713
b 2.1117 0.6172 4.3899 -0.4819 18.3944 2.2993 21.1471
ab 1.9533 6.1790 6.8325 -0.5864 -0.8654 -0.1082 0.0468
c 0.3194 0.4048 -0.1856 9.2202 4.7672 0.5959 1.4204
ac 0.2978 3.9850 -0.2963 9.1742 -0.1714 -0.0214 0.0018
bc 3.2269 0.6192 -0.2629 -0.3842 3.9172 0.4897 0.9591
abc 2.9522 6.2132 -0.3236 -0.4811 -0.1521 -0.0190 0.0014
d 0.2118 -0.0272 3.6584 2.3246 -0.0456 -0.0057 0.0001
ad 0.1931 -0.1583 5.5618 2.4426 -0.1045 -0.0131 0.0007
bd 2.1146 -0.0216 3.5802 -0.1108 -0.0460 -0.0058 0.0001
abd 1.8704 -0.2747 5.5940 -0.0607 -0.0969 -0.0121 0.0006
cd 0.3266 -0.0187 -0.1311 1.9034 0.1180 0.0148 0.0009
acd 0.2926 -0.2442 -0.2531 2.0138 0.0501 0.0063 0.0002
bcd 3.2514 -0.0340 -0.2255 -0.1220 0.1104 0.0138 0.0008
abcd 2.9618 -0.2896 -0.2556 -0.0301 0.0919 0.0115 0.0005
Total = 22.4902

Copyright held by The Minerals, Metals & Materials Society, 1999

Direct questions about this or any other JOM page to jom@tms.org.

Search TMS Document Center Mehta's Main Text Other Hypertext Articles JOM TMS OnLine