13.24 The following table (from A. Hald, Statistical Theory with Engineering Applications, John Wiley &

Sons, New York, 1952) gives tensile strengths (in deviations from 340) for wires taken from nine cables to be used for a high-voltage network. Each cable is made from 12 wires. We want to know whether the mean strengths of the wires in the nine cables are the same.

If the cables are different, which ones differ? Use a P-value in your analysis of variance.

Cable Tensile Strength 1 5−13 −5 −2 −10 −6 −5 0−3 2 −7 −5 2 −11 −13 −8 8 −3 −12 −12 −10 5 −6 −12 −10 3 0−10 −15 −12 −2 −8 −5 0−4 −1 −5 −11 4 −12 4 2 10 −5 −8 −12 0 −5 −3 −3 0 5 7 1 5 0 10 6 5 2 0−1 −10 −2 6 1 0 −5 −4 −1 0 2 5 1−2 6 7 7 −1 0 2 1 −4 2 7 5 1 0 −4 2 8 −1 0 7 5 10 8 1 2−3 6 0 5 9 2 6 7 8 15 11 −7 7 10 7 8 1 The GLM Procedure Duncan’s Multiple Range Test for moisture NOTE: This test controls the Type I comparisonwise error rate, not the experimentwise error rate.
Alpha 0.05 Error Degrees of Freedom 25 Error Mean Square 4960.813 Number of Means 2 3 4 5 Critical Range 83.75 87.97 90.69 92.61 Means with the same letter are not significantly different.
Duncan Grouping Mean N aggregate A 610.67 6 5 A A 610.50 6 3 A A 569.33 6 2 A A 553.33 6 1 B 465.17 6 4