Chapter 12, Problem 35PS

A vice president for marketing recruits 20 college graduates for management training. Each of the 20 individuals is randomly assigned to one of two groups (10 in each group). A “traditional� method of training $\left(T\right)$ is used in one group, and an “experimental method $\left(E\right)$ is used in the other. After the graduates spend six months on the job, the vice president ranks them on the basis of their performance, from 1 (worst) to 20 (best), with the following results (stored in the file TestRank):

$\begin{array}{l}\text{T:}\text{1 2 3 5 9 10 12 13 14 15}\\ \text{E}\text{: 4 6 7 8 11 16 17 18 19 20}\end{array}$

Is there evidence of a difference in the median performance between the two methods? $\text{(Use}\alpha =\mathrm{0.05.})$