Null Hypothesis or H0: May & August Delivery Times Are Equal.
Alternative Hypothesis or H1: May Delivery Times Are Shorter Than August Delivery Times.
Organize the 2 sets of data into one table with Times in ascending order. The Month for each Time is shown and Rank numbers are given in ascending order. Equal Times are given "split" Rank numbers; 62 & 62 are given an equal Rank of 4.5 (the mean of 4 & 5, which would have been their Ranks for ascending Time value had they been unequal).
TIME---MONTH----------RANK
49---------May----------------1
50---------August------------2
54---------May----------------3
62---------May----------------4.5
62---------May----------------4.5
64---------August-------------6
65---------August-------------7
66---------May-----------------8
68---------May-----------------9.5
68---------August-------------9.5
72---------August------------11
74---------August------------12
Sample sizes are named here as n1 (for May Times) equal to 6 and n2 (for August Times) equal to 6.
Label the sum of the Rank Numbers for May Times as R since n1 has been marked as the May sample size.
Then R = 1+3+4.5+4.5+8+9.5 or 30.5.
Enter a Table Of Lower & Upper Critical Values For The Wilcoxon Rank-Sum Test
for a 1-Tailed Test with (α, n1, n2) = (0.05, 6, 6). The Table will return 28 & 50 as the critical values.
Here R at 30.5 falls just inside the range 28-to-50 so one "fails to reject" the null hypothesis H0 and
concludes that the May & August delivery times are equal for all practical purposes at the 0.05 level of significance.