Shoplifting Incidents
In a large department store, the owner wishes to see whether the number of shoplifting incidents per day will change if the number of uniformed security officers is doubled. A random sample of 7 days before security is increased and 7 days after the increase shows the number of shoplifting incidents.
Is there enough evidence to support the claim, at α = 0.05, that there is a difference in the number of shoplifting incidents before and after the increase in security?
Day |
Number of shoplifting incidents | |
Before | After | |
Monday | 7 | 5 |
Tuesday | 2 | 3 |
Wednesday | 3 | 4 |
Thursday | 6 | 3 |
Friday | 5 | 1 |
Saturday | 8 | 6 |
Sunday | 12 | 4 |
Step 1 State the hypotheses and identify the claim.
H_{0} : There is no difference in the number of shoplifting incidents before and after the increase in security.
H_{1} : There is a difference in the number of shoplifting incidents before and after the increase in security (claim).
Step 2 Find the critical value from Table K because n \leq 30. Since n=7 and \alpha=0.05 for this two-tailed test, the critical value is 2 . See Figure 13-2.
Step 3 Find the test value.
a. Make a table as shown.
\begin{array}{|l|c|c|c|c|c|c|} \hline Day & Before, \boldsymbol{X}_{\boldsymbol{B}} & After, \boldsymbol{X}_{\boldsymbol{A}} & \begin{array}{c}\text { Difference } \\ \boldsymbol{D}=\boldsymbol{X}_{\boldsymbol{B}}-\boldsymbol{X}_{\boldsymbol{A}}\end{array} & \begin{array}{c}\text { Absolute } \\ \text { value } \boldsymbol{D} \mid\end{array} & Rank & \begin{array}{c}\text { Signed } \\ \text { rank }\end{array} \\ \hline Mon. & 7 & 5 & & & & \\ Tues. & 2 & 3 & & & & \\ Wed. & 3 & 4 & & & & \\ Thurs. & 6 & 3 & & & & \\ Fri. & 5 & 1 & & & & \\ Sat. & 8 & 6 & & & & \\ Sun. & 12 & 4 & & & & \\ \hline \end{array}
b. Find the differences (before minus after), and place the values in the Difference column.
\begin{aligned}& 7-5=2 \quad 6-3=3 \quad 8-6=2 \\& 2-3=-1 \quad 5-1=4 \quad 12-4=8 \\& 3-4=-1\end{aligned}
c. Find the absolute value of each difference, and place the results in the Absolute value column. (Note: The absolute value of any number except 0 is the positive value of the number. Any differences of 0 should be ignored.)
\begin{array}{rlr}|2|=2 & |3|=3 & |2|=2 \\|-1|=1 & |4|=4 & |8|=8 \\|-1|=1 & &\end{array}
d. Rank each absolute value from lowest to highest, and place the rankings in the Rank column. In the case of a tie, assign the values that rank plus 0.5.
\begin{array}{|l|l|l|l|l|l|l|l|} \hline \text{Value }& 2 & 1 & 1 & 3 & 4 & 2 & 8 \\ \hline \text{Rank }& 3.5 & 1.5 & 1.5 & 5 & 6 & 3.5 & 7 \\ \hline \end{array}
e. Give each rank a plus or minus sign, according to the sign in the Difference column. The completed table is shown here.
\begin{array}{|l|c|c|c|c|c|c|} \hline Day & Before, \boldsymbol{X}_{\boldsymbol{B}} & After, \boldsymbol{X}_{\boldsymbol{A}} & \begin{array}{c}\text { Difference } \\ \boldsymbol{D}=\boldsymbol{X}_{\boldsymbol{B}}-\boldsymbol{X}_{\boldsymbol{A}}\end{array} & \begin{array}{c}\text { Absolute } \\ \text { value }|\boldsymbol{D}|\end{array} & Rank & \begin{array}{c}\text { Signed } \\ \text { rank }\end{array} \\ \hline Mon. & 7 & 5 & 2 & 2 & 3.5 & +3.5 \\ Tues. & 2 & 3 & -1 & 1 & 1.5 & -1.5 \\ Wed. & 3 & 4 & -1 & 1 & 1.5 & -1.5 \\ Thurs. & 6 & 3 & 3 & 3 & 5 & +5 \\ Fri. & 5 & 1 & 4 & 4 & 6 & +6 \\ Sat. & 8 & 6 & 2 & 2 & 3.5 & +3.5 \\ Sun. & 12 & 4 & 8 & 8 & 7 & +7 \\ \hline \end{array}
f. Find the sum of the positive ranks and the sum of the negative ranks separately.
Positive rank sum \quad(+3.5)+(+5)+(+6)+(+3.5)+(+7)=+25 Negative rank sum \quad(-1.5)+(-1.5) \quad=-3
g. Select the smaller of the absolute values of the sums (|-3|), and use this absolute value as the test value w_{s}. In this case, w_{s}=|-3|=3.
Step 4 Make the decision. Reject the null hypothesis if the test value is less than or equal to the critical value. In this case, 3>2; hence, the decision is to not reject the null hypothesis.
Step 5 Summarize the results. There is not enough evidence at \alpha=0.05 to support the claim that there is a difference in the number of shoplifting incidents before and after the increase in security. Hence, the security increase probably made no difference in the number of shoplifting incidents.
TABLE K Critical Values for the Wilcoxon Signed-Rank Test | ||||
Reject the null hypothesis if the test value is less than or equal to the value given in the table | ||||
n | One-tailed, 𝜶 = 0.05 |
𝜶 = 0.025 | 𝜶 = 0.01 | 𝜶 = 0.005 |
Two-tailed, 𝜶 = 0.10 |
𝜶 = 0.05 | 𝜶 = 0.02 | 𝜶 = 0.01 | |
5 | 1 | − | − | − |
6 | 2 | 1 | − | − |
7 | 4 | 2 | 0 | − |
8 | 6 | 4 | 2 | 0 |
9 | 8 | 6 | 3 | 2 |
10 | 11 | 8 | 5 | 3 |
11 | 14 | 11 | 7 | 5 |
12 | 17 | 14 | 10 | 7 |
13 | 21 | 17 | 13 | 10 |
14 | 26 | 21 | 16 | 13 |
15 | 30 | 25 | 20 | 16 |
16 | 36 | 30 | 24 | 19 |
17 | 41 | 35 | 28 | 23 |
18 | 47 | 40 | 33 | 28 |
19 | 54 | 46 | 38 | 32 |
20 | 60 | 52 | 43 | 37 |
21 | 68 | 59 | 49 | 43 |
22 | 75 | 66 | 56 | 49 |
23 | 83 | 73 | 62 | 55 |
24 | 92 | 81 | 69 | 61 |
25 | 101 | 90 | 77 | 68 |
26 | 110 | 98 | 85 | 76 |
27 | 120 | 107 | 93 | 84 |
28 | 130 | 117 | 102 | 92 |
29 | 141 | 127 | 111 | 100 |
30 | 152 | 137 | 120 | 109 |
Source: From Some Rapid Approximate Statistical Procedures, Copyright 1949, 1964 Lerderle Laboratories, American Cyanamid Co.,
Wayne, N.J. Reprinted with permission.