In an experiment to compare the tensile strengths of 5 dierent types of copper wire, a pooled t-test with

= :05 was used to group the types of wire according to equal pairwise mean strength. The major problem

that will result from this procedure is

A. the experimentwise Type I error rate will be much larger than the nominal = :05 of the t-test.

B. the number of tests that need to be conducted is excessive.

C. the assumption of independence will be violated.

D. the Type II error rate will not be constant.

E. none of the above, this is the proper procedure.