II.

Computational

1) A sample of 500 shoppers was selected in a large metropolitan area to determine

various informations concerning consumer behavior. Among the questions asked
was, “Do you enjoy shopping for clothing?” The results are summarized in the
following contingency table:

Gender
Enjoy Shopping for Clothing
MALE FEMALE
YES 136 224
NO 104 36

Is there evidence of significant difference between the proportions of males and

females who enjoy shopping for clothing at 0.01 level of significance. Determine the
p-value and interpret its meaning.

Steps:
i. Null Hypothesis.
H0: There is no significant difference between the proportions of males and
females who enjoy shopping for clothing
H1: There is a significant difference between the proportions of males and females
who enjoy shopping for clothing

ii. Statistical Test: Chi-Square Test is appropriate

iii. Significance level: α= 0.01 for N = 500
iv. Sampling Distribution.
𝑁 2
𝑁 (|𝐴𝐷 − 𝐵𝐶 | − 2 )
𝑋2 =
(𝐴 + 𝐵)(𝐶 + 𝐷 )(𝐴 + 𝐶 )(𝐵 + 𝐷 )
with df=1. We will use the Appendix Table C to get the critical value. We will
compare the result to X2.

v. Rejection region.
The region of rejection for this test consists of all values of X2 for which the
probability of observing a value as larger when H0 is true is less than α= 0.01.

vi. Decision: The table below shows data.

Enjoy Shopping for Gender

Clothing MALE FEMALE
YES 136 224 360
NO 104 36 140
TOTAL 240 260 500
 𝑁 2
𝑁 (|𝐴𝐷 − 𝐵𝐶 | − 2 )
𝑋2 =
(𝐴 + 𝐵)(𝐶 + 𝐷 )(𝐴 + 𝐶 )(𝐵 + 𝐷 )
500 2
500 (|136 ∙ 36 − 224 ∙ 104| − 2 )
𝑋2 =
(136 + 224)(104 + 36)(136 + 104)(224 + 36)

500(|4896 − 23296| − 250)2

𝑋2 =
360 ∙ 140 ∙ 240 ∙ 260

500 ∙ 329422500 5 ∙ 3294225 16471125

𝑋2 = == = ≈ 52.4
360 ∙ 140 ∙ 240 ∙ 260 36 ∙ 14 ∙ 24 ∙ 26 314496

Using Appendix Table C with df = 1 and α = 0.01, we get the critical value = 6.64. The
computed value = 52.4 > critical value = 6.64. Therefore, we may reject H0. There is
enough evidence to conclude that there is a significant difference between the
proportions of males and females who enjoy shopping for clothing at the 0.01 level of
significance.

2) An athletics coach wishes to test the value to his athletes of an intensive period of
weight training and so he selects twelve 400-meter runners from his region and
records their times, in seconds, to complete the distance. They then undergo his
programme of weight training and have their times, in seconds, for 400 meters
measured again, The table below summarizes the results:
Athletes A B C D E F G H I J K L
Before 51.0 49.8 49.5 50.1 51.6 48.9 52.4 50.6 53.1 48.6 52.9 53.4
After 50.6 50.4 48.9 49.1 51.6 47.8 53.5 49.9 51.0 48.5 50.6 51.7

Test the hypothesis that the training program significantly improved athletes’ times for
the 400 meters at 0.05 level of significance.

Steps:
i. Null Hypothesis.
H0: The training programme has no effect.
H1: The training programme improves athlete’s time

ii. Statistical Test: Wilcoxon Signed Rank Test

iii. Significance level: α= 0.05 for N = no. of pairs (12) minus any pairs whose di=0.

iv. Sampling Distribution.

We can use Appendix Table H to find the upper-tail probability values for
sampling distribution for T+ for N≤15.
v. Rejection region.
The region of rejection for this test consists of all values of T+ (the sum of positive
ranks) for which the probability of observing a value as larger when H0 is true is
less than α= 0.05. Using the tables, with α= 0.05 and N=12-1-11(1 zero
difference), the critical region is T>52.
 vi. Decision: The table below shows data.

Let d= (time before)-(time after) be the difference

Athletes A B C D E F G H I J K L
Before 51.0 49.8 49.5 50.1 51.6 48.9 52.4 50.6 53.1 48.6 52.9 53.4
After 50.6 50.4 48.9 49.1 51.6 47.8 53.5 49.9 51.0 48.5 50.6 51.7
d +0.4 -0.6 +0.6 +1.0 0.0 +1.3 -1.1 +0.7 +2.1 +0.1 +2.3 +1.7
|d| 0.4 0.6 0.6 1.0 0.0 1.3 1.1 0.7 2.1 0.1 2.3 1.7
rank 2 3.5 3.5 6 8 7 5 10 1 11 9
Signed
+2 -3.5 +3.5 +6 +8 -7 +5 +10 +1 +11 +9
rank

𝑇 + = 2 + 3.5 + 6 + 8 + 5 + 10 + 1 + 11 + 9 = 55.5
𝑇 − = 3.5 + 7+= 10.5

Thus, T=55.5
The value of T lies in the critical region. Thus, we may reject the null hypothesis at 0.05.
Therefore, there is evidence that the weight training programme improves athlete’s time
for 400 meters.

3) Custer and Galli (2002) flew a light plane to follow great blue herons (Ardea herodias)
and great egrets (Casmero dius albus) from their resting site to their first feeding site
at Peltier Lake, Minnesota, and recorded the type of substrate each bird landed on. Is
there evidence that the two species of birds use the substrates in different
proportions at 0.05 level of significance?

Substrate Heron Egret

Vegetation 15 8
Shoreline 20 5
Water 14 7
Structures 6 1

Steps:
i. Null Hypothesis.
H0: The there is no evidence that the two species of birds use the substrates in
different proportions.
H1: The two species of birds use the substrates in different proportions.
ii. Statistical Test: Chi-Square Test for Independence
iii. Significance level: α= 0.05 for N = 76
iv. Sampling Distribution.
𝑟 𝑘 2
2
(𝑛𝑖𝑗 − 𝐸𝑖𝑗 )
𝑋 = ∑∑
𝐸𝑖𝑗
𝑖=1 𝑗=1

We can use Appendix Table C with df=(r-1)(k-1) and α= 0.05. The probability
associated with the occurrence of values as larger than an observed X2 when
H0 is true.
 v. Rejection region.
The region of rejection for this test consists of all values of X2 that is large. The
probability associated with their occurrence when H0 is true is ≤0.05.

vi. Decision. Expected Frequency = (Row Total * Column Total)/N.

The table shown below is the two-way table computation. The top number in each
cell of the table is the observed values and the bottom number is the expected
values that are shown in parentheses.

Substrate Heron Egret TOTAL

15 8
Vegetation 23
(16.64) (6.36)
20 5
Shoreline 25
(18.09) (6.91)
14 7
Water 21
(15.20) (5.80)
6 1
Structures 7
(5.07) (1.93)
TOTAL 55 21 76

𝑟 𝑘 2
(𝑛𝑖𝑗 − 𝐸𝑖𝑗 )
𝑋2 = ∑ ∑
𝐸𝑖𝑗
𝑖=1 𝑗=1

2
(15 − 16.64)2 (8 − 6.36)2 (20 − 18.09)2 (5 − 6.91)2 (14 − 15.20)2
𝑋 = + + + + +
16.64 6.36 18.09 6.91 15.20
(7 − 5.80)2 (6 − 5.07)2 (1 − 1.93)2
+ + +
5.80 5.07 1.93

2.69 2.69 3.64 3.64 1.44 1.44 0.86 0.86

𝑋2 = + + + + + + +
16.64 6.36 18.09 6.91 15.20 5.80 5.07 1.93

𝑋 2 = 0.16 + 0.42 + 0.20 + 0.53 + 0.09 + 0.25 + 0.17 + 0.45

𝑋 2 = 2.27

Using Appendix Table C with df=(r-1)(k-1)=(4-1)(2-1)=3(1)=3 and α= 0.05. We fail to

reject H0 because 2.27 <7.82. We have statistically significant evidence at a =0.05 to
show that H0 is true. Therefore, there is no evidence that the two species of birds use
the substrates in different proportions.
4) Many states are considering lowering the blood-alcohol level at which a driver is
designated as driving under the influence of alcohol (DUI). An investigator for a
legislative committee designed the following test to study the effect of alcohol on
reaction time. Ten participants consumed a specified amount of alcohol. Another
group of ten participants consumed the same amount of nonalcoholic drink, a
placebo. The two groups did not know whether they were receiving alcohol or
placebo. The twenty participants’ average reaction times (in seconds) to a series of
simulated driving situations are reported as shown in the table. Is there a significant
difference in the reaction time of the two groups at 0.05 level of significance?

Placebo 0.90 0.37 1.63 0.83 0.95 0.78 0.86 0.61 0.38 1.97
Alcohol 1.46 1.45 1.76 1.44 1.11 3.07 0.98 1.27 2.56 1.32

Steps:
i. Null Hypothesis.
H0: There is no significant difference in the reaction time of the two groups.
H1: There is a significant difference in the reaction time of the two groups.

ii. Statistical Test: Mann-Whitney U Test

iii. Significance level: α= 0.05 n1=10 (Placebo) and n2=10 (Alcohol)

iv. Sampling Distribution.

We use the statistic for Mann Whitney U Test. It is denoted by U (the smaller of
U1 and U2)

𝑛1 (𝑛1 + 1)
𝑈1 = 𝑛1 𝑛2 + − 𝑅1
2

𝑛2 (𝑛2 + 1)
𝑈2 = 𝑛1 𝑛2 + − 𝑅2
2

where R1=sum of ranks of group 1 and R2= sum of ranks of group 2. Then we
use the critical values for U.

v. Rejection region. The rejection region can be determine from the critical values
and the sample size n1=n2=10 with α= 0.05. Thus, using the table, the decision
rule is to reject H0 if the value of U≤23.

vi. Decision:

The data shown below are arranged in ascending order in the table.

Group X: Placebo (n1=10)

0.90 0.37 1.63 0.83 0.95 0.78 0.86 0.61 0.38 1.97
Group Y: Alcohol (n2=10)
1.46 1.45 1.76 1.44 1.11 3.07 0.98 1.27 2.56 1.32
 GROUP ordered from smallest to largest RANK
Placebo Alcohol Placebo Alcohol Placebo Alcohol
X 0.37 1
X 0.38 2
X 0.61 3
X 0.78 4
X 0.83 5
X 0.86 6
X 0.9 7
X 0.95 8
Y 0.98 9
Y 1.11 10
Y 1.27 11
Y 1.32 12
Y 1.44 13
Y 1.45 14
Y 1.46 15
X 1.63 16
Y 1.76 17
X 1.97 18
Y 2.56 19
Y 3.07 20
R1=70 R2=140

𝑛1 (𝑛1 + 1) 10(10 + 1)
𝑈1 = 𝑛1 𝑛2 + − 𝑅1 = 10 ∙ 10 + − 70 = 85
2 2

𝑛2 (𝑛2 + 1) 10(10 + 1)
𝑈2 = 𝑛1 𝑛2 + − 𝑅2 = 10 ∙ 10 + − 140 = 15
2 2

Thus, U=smaller=15

Since U=15≤23, we may reject H0. Therefore, there is a significant difference in the
reaction time of the two groups.

=============================== END ===============================