STA408: Statistics for Science and Engineering

Tutorial 3

Hypothesis Testing for a Single Population Mean

1. A researcher wishes to see if the mean number of days that a basic, low-price, small automobile sits
on a dealer’s lot is 29. A sample of 30 automobile dealers has a mean of 30.1 days for basic, low-
price, small automobiles. At 𝛼 = 0.05, test the claim that the mean time is greater than 29 days. The
standard deviation of the population is 3.8 days.
(Answer: 𝐻1 : 𝜇 > 29, critical value = 1.6449, test statistic = 1.5855, do not reject 𝐻0 )

2. The Medical Rehabilitation Education Foundation reports that the average cost of rehabilitation for
stroke victim is RM24,672. To see if the average cost of rehabilitation is different at a particular
hospital, a researcher selects a random sample of 35 stroke victims at the hospital and finds that
the average cost of their rehabilitation is RM26,343. The standard deviation of the population is
RM3,251. At 𝛼 = 0.01, can it be concluded that the average cost of stroke rehabilitation at a
particular hospital is different from RM24,672?
(Answer: 𝐻1 : 𝜇 ≠ 24,672, critical values = ±2.5756, test statistic = 3.0408, reject 𝐻0 )

3. A store manager hypothesizes that the average number of pages a person copies on the store’s copy
machine is not equal to 40. A sample of 50 customers’ orders is selected and is summarised in the
Minitab output below.
One-Sample Z: no_of_pages

Test of μ = 40 vs ≠ 40
The assumed standard deviation = 30.9

Variable N Mean StDev SE Mean 98% CI Z P

no_of_pages 50 29.26 30.94 4.37 (19.09, 39.43) -2.46 0.014
(a) Based on the Minitab output above, is there enough evidence to support the store manager’s
claim at 𝛼 = 0.02? Use the 𝑝-value hypothesis-testing method.
(b) State the 98% confidence interval for the mean of all the number of pages a person copies in
the store’s copy machine. Is the interval consistent with the conclusion in (a)? Explain your
answer.
(Answer: (a) 𝐻1 : 𝜇 ≠ 40, 𝑝-value = 0.014 < 𝛼 = 0.02, reject 𝐻0 )
(b) (19.09, 39.43); Yes, because the value 40 is not in the interval)

4. Suppose that an engineer is interested in testing the bias in a pH meter. Data are collected on a
neutral substance (pH = 7.0). A sample of the measurements was taken and summarised in the
Minitab output below. Test at 𝛼 = 0.10 whether the pH meter is biased?
One-Sample T: pH-meter
Test of μ = 7 vs ≠ 7
Variable N Mean StDev SE Mean 95% CI T P
pH-meter 10 7.0250 0.0440 0.0139 (6.9935, 7.0565) 1.80 0.106

(Answer: 𝐻1 : 𝜇 ≠ 7, 𝑝-value = 0.106 > 𝛼 = 0.10, do not reject 𝐻0 )

5. A medical investigation claims that the average number of infections per week at a hospital is 16.3.
A random sample of 10 weeks had a mean number of 17.7 infections. The sample standard
deviation is 1.8. Is there enough evidence to reject the investigator’s claim at 𝛼 = 0.05? Assume
that the population distribution of the number of infections is approximately normally distributed.
(Answer: 𝐻1 : 𝜇 ≠ 16.3, critical values = ±2.262, test statistic = 2.459, reject 𝐻0 )

6. The Edison Electric Institute has published figures on the number of kilowatt hours used annually
by various home appliances. It claimed that a vacuum cleaner uses an average of 46 kilowatt hours
STA408 Tutorial 3 Chapter 3: Hypothesis Testing

per year. If a random sample of 12 hours included in a planned study indicates that vacuum
cleaners use an average of 42 kilowatt hours per year with a standard deviation of 11.9 kilowatt
hours, does this suggest at the 0.05 level of significance that vacuum cleaners use, on average, less
than 46 hours annually? Assume the population of kilowatt hours to be normal.
(Answer: 𝐻1 : 𝜇 < 46, critical value = −1.796, test statistic = −1.164, do not reject 𝐻0 )

7. It is claimed that an electrical firm manufactures light bulbs that have a lifetime that is
approximately normally distributed with a mean of 800 hours and a standard deviation of 40 hours.
Would you agree with this claim if a random sample of 30 bulbs has an average life of 780 hours at
2% significance level?
(Answer: 𝐻1 : 𝜇 ≠ 800, critical values = ±2.3263, test statistic = −2.7386, reject 𝐻0 ; No)

8. A coin manufacturer purchases a particular material from a supplier. The manufacturer selects 11
shipments from the supplier and measures the percentage of impurities of the raw material from
each shipment. The sample mean and variance are given as 2.09 and 0.317 respectively. At 5%
level of significance, test whether the average percentage of impurities is different from 2.4.
(Answer: 𝐻1 : 𝜇 ≠ 2.4, critical values = ±2.228, test statistic = −1.826, do not reject 𝐻0 )

Hypothesis Testing for Two Population Means (Independent Samples)

9. The Minitab output below displays the analysis of a two-sample 𝑡-test.
Two-Sample T-Test and CI
SE
Sample N Mean StDev Mean
1 35 650 100 17
2 27 500.0 80.0 15
Difference = μ (1) - μ (2)
Estimate for difference: 150.0
95% CI for difference: (102.9, 197.1)
T-Test of difference = 0 (vs ≠): T-Value = 6.37 P-Value = 0.000 DF = 60
Both use Pooled StDev = 91.8695
(a) Based on the output, what is the assumption of variances for the two populations?
(b) Is there a significant difference between the two population means at 5% significance level?
(Answer: 𝐻1 : 𝜇1 − 𝜇2 ≠ 0, 𝑝-value = 0.000 < 𝛼 = 0.05, reject 𝐻0 )

10. A survey found that the average hotel room rate in Shah Alam is RM176.84 and the average room
rate in Klang is RM161.22. Assume that the data were obtained from two samples of 50 hotels each
and that the standard deviations of the populations are RM11.24 and RM9.66, respectively. At
𝛼 = 0.05, can it be concluded that there is a significant difference in the rates?
(Answer: 𝐻1 : 𝜇𝑆𝐴 − 𝜇𝐾 ≠ 0, critical values = ±1.96, test statistic = 7.4524, reject 𝐻0 )

11. A researcher hypothesizes that the average number of sports that colleges offer for males is greater
than the average number of sports that colleges offer for females. The data collected is summarised
in the Minitab output below.
Two-Sample T-Test and CI: Males, Females
Two-sample T for Males vs Females
N Mean StDev SE Mean
Males 50 8.56 3.26 0.46
Females 50 7.94 3.27 0.46
Difference = μ (Males) - μ (Females)
Estimate for difference: 0.620
90% lower bound for difference: -0.222
T-Test of difference = 0 (vs >): T-Value = 0.95 P-Value = 0.172 DF = 98
Both use Pooled StDev = 3.2626
(a) Show that the test statistic, 𝑡 = 0.95.
(b) At 𝛼 = 0.10, is there enough evidence to support the claim? Use 𝑝-value.

2
STA408 Tutorial 3 Chapter 3: Hypothesis Testing

(Answer: 𝐻1 : 𝜇𝑀 − 𝜇𝐹 > 0, 𝑝-value = 0.172 > 𝛼 = 0.10, do not reject 𝐻0 )

12. According to a Research, children (ages 2–11) spend an average of 21.5 hours watching television
per week while teens (ages 12–17) spend an average of 20.6 hours. Based on the sample statistics
obtained below, is there sufficient evidence to conclude a difference in average television watching
times between the two groups? Use 𝛼 = 0.01
Children Teens
Sample mean 22.45 18.5
Sample variance 16.4 18.2
Sample size 15 15
Assume that the two population distributions are approximately normally distribution with equal
variances.
(Answer: 𝐻1 : 𝜇𝐶 − 𝜇𝑇 ≠ 0, 𝜈 = 28, critical values = ±2.763, test statistic = 2.601, do not reject 𝐻0 )

13. Engineers at a large automobile manufacturing company are trying to decide whether to purchase
brand A or brand B tyres for the company’s new models. To help them arrive at a decision, an
experiment is conducted using 12 of each brand. The tyres are run until they wear out. The results
are as follows.
Two-Sample T-Test and CI
Sample N Mean StDev SE Mean
A 12 37900 5100 1472
B 12 39800 5900 1703
Difference = μ (A) - μ (B)
Estimate for difference: -1900
95% CI for difference: (-6569, 2769)
T-Test of difference = 0 (vs ≠): T-Value = -0.84 P-Value = 0.408 DF = 22
Both use Pooled StDev = 5514.5263
Assume the populations to be approximately normally distributed.
(a) Show that the test statistic is −0.84.
(b) Is there sufficient evidence at 𝛼 = 0.05 to conclude that there is a significant difference in the
average wear of the two brands of tyres?
(Answer: 𝐻1 : 𝜇𝐴 − 𝜇𝐵 ≠ 0, 𝑝-value = 0.408 > 𝛼 = 0.05, do not reject 𝐻0 )
(c) State the 95% confidence interval for the difference in the average wear of the two brands of
tyres. Determine if the interval supports the conclusion in (b). Support your answer.
(Answer: Yes)

14. The average size of a farm in Pulau Meranti is 191 m2. The average size of a farm in Pulau Jati is
199 m2. Assume the data were obtained from two samples with standard deviation of 38 and
12 m2, respectively, and sample sizes of 8 and 10, respectively. Can it be concluded that at 𝛼 = 0.05
that the average size of the farms in the two Pulau is different? Assume the populations are
normally distributed with unequal variances.
(Answer: 𝐻1 : 𝜇𝑀 − 𝜇𝐽 ≠ 0, 𝜈 = 8, critical values = ±2.306, test statistic = −0.573, do not reject
𝐻0 )

15. The number of points held by a sample of National Hockey League’s scorers for both the Eastern
region and the Western region are summarised in the Minitab output below. Assume that the
population distributions are normally distributed.
(a) Show that the test statistic, 𝑡 = 1.17.
(b) At 𝛼 = 0.05, is there enough evidence to conclude that there is a difference in means based
on output? Use 𝑝-value.
(Answer: 𝐻1 : 𝜇𝐸 − 𝜇𝑊 ≠ 0, 𝑝-value = 0.257 > 𝛼 = 0.05, do not reject 𝐻0 )
(c) State the 95% confidence interval for the mean difference of the two populations. Is the
interval consistent with the conclusion in (b)? Explain your answer.

3
STA408 Tutorial 3 Chapter 3: Hypothesis Testing

Two-Sample T-Test and CI: Eastern, Western

Two-sample T for Eastern vs Western
N Mean StDev SE Mean
Eastern 11 65.73 9.12 2.8
Western 9 60.2 11.4 3.8
Difference = μ (Eastern) - μ (Western)
Estimate for difference: 5.51
95% CI for difference: (-4.49, 15.50)
T-Test of difference = 0 (vs ≠): T-Value = 1.17 P-Value = 0.259 DF = 15

Hypothesis Testing for Paired Samples (Dependent Samples)

16. A company is considering installing new machines to assemble its products. The company is
considering two types of machines, but it will buy only one type. The company selected eight
assembly workers and asked them to use these two types of machines to assemble products. The
following table gives the time taken (in minutes) to assemble one unit of the product on each type
of machine for each of these eight workers. Test at 5% significance level whether the mean time
taken to assemble a unit of product is different for the two types of machines. Assume the
population of the paired differences is (approximately) normally distributed.
Machine
17. I 23 26 19 24 27 22 20 18
Machine II 21 24 23 25 24 28 24 23
(Answer: 𝐻1 : 𝜇𝑑 ≠ 0, critical value = ±2.365, test statistic = −1.2835, do not reject 𝐻0 )

17. A study was conducted at the Department of Veterinary Medicine to determine if the “strength” of
a wound from surgical incision is affected by the temperature of the knife. Eight dogs were used in
the experiment. “Hot” and “cold” incisions were made on the abdomen of each dog, and the strength
was measured. The Minitab output of the summarised data is as below.
Paired T-Test and CI: Hot_knife, Cold_knife
Paired T for Hot_knife - Cold_knife
N Mean StDev SE Mean
Hot_knife 8 6819 4105 1451
Cold_knife 8 6093 3690 1305
Difference 8 726 2072 733

98% lower bound for mean difference: -1118

T-Test of mean difference = 0 (vs > 0): T-Value = 0.99 P-Value = 0.177
Assume the populations of the strength to be approximately normally distributed.
(a) Show that the test statistic is 0.99.
(b) Test at 10% significance level whether the hot incision is stronger than the cold incision.
(Answer: 𝐻1 : 𝜇𝑑 > 0, 𝑝-value = 0.177 < 𝛼 = 0.10, do not reject 𝐻0 )

18. The following Minitab output represents the times (in seconds) taken by each contestant to eat the
first Whoopie Pie and the ninth (last) Whoopie Pie in a Whoopie Pie eating contest and 13
contestants who finished all nine Whoopie Pies were selected. Assume that the population of paired
differences is (approximately) normally distributed, can you conclude that it takes at least 15
seconds more, on average, to eat the ninth pie than to eat the first pie at 10% significance level?
Paired T-Test and CI: Last_Pie, First_Pie
Paired T for Last_Pie - First_Pie
N Mean StDev SE Mean
Last_Pie 13 84.23 16.99 4.71
First_Pie 13 62.62 8.22 2.28
Difference 13 21.62 13.89 3.85
90% lower bound for mean difference: 16.39
T-Test of mean difference = 15 (vs > 15): T-Value = 1.72 P-Value = 0.056

4
STA408 Tutorial 3 Chapter 3: Hypothesis Testing

(Answer: 𝐻1 : 𝜇𝑑 > 15, 𝑝-value = 0.056 < 𝛼 = 0.10, reject 𝐻0 )

Hypothesis Testing for Population Variance

19. A cigarette manufacturer wishes to test the claim that the variance of the nicotine content of its
cigarettes is 0.644. Nicotine content is measured in milligrams, and assume that it is normally
distributed. A sample of 20 cigarettes has a standard deviation of 1.00 milligram. At 𝛼 = 0.05, is
there enough evidence to reject the manufacturer’s claim?
(Answer: 𝐻1 : 𝜎 2 ≠ 0.644, critical values = 8.907, 32.852, test statistic = 29.50, do not reject 𝐻0 )

20. A manufacturing process produces machine parts with measurements the standard deviation of
which must be no more than 0.52 mm. A random sample of 20 parts in a given lot revealed a
standard deviation in measurement of 0.568 mm. Is there sufficient evidence at 𝛼 = 0.05 to
conclude that the standard deviation of the parts is outside the required guidelines? Assume the
variable to be normally distributed.
(Answer: 𝐻1 : 𝜎 > 0.52, critical value = 30.144, test statistic = 22.67, do not reject 𝐻0 )

21. A researcher knows from past studies that the standard deviation of the time it takes to inspect a
car is 16.8 minutes.
Test and CI for One Variance
Method

Null hypothesis σ = 16.8

Alternative hypothesis σ ≠ 16.8

The chi-square method is only for the normal distribution.

Statistics

N StDev Variance
24 12.5 156

Tests
Test
Method Statistic DF P-Value
Chi-Square 12.73 23 0.085

(a) Show that the test statistic is 12.73.

(b) Based on the Minitab output below, can it be concluded at 𝛼 = 0.05 that the standard
deviation has changed? Use 𝑝-value.
(Answer: 𝐻1 : 𝜎 ≠ 16.8, 𝑝-value = 0.085 > 𝛼 = 0,05, do not reject 𝐻0 )

Hypothesis Testing for Ratio of Two Population Variance

22. A random sample of daily high temperatures in January and February is listed below. At 𝛼 = 0.05
can it be concluded that there is a difference in variances in high temperature between the two
months. Assume the variables are normally distributed.
Jan 31 31 38 24 24 42 22 43 35
Feb 31 29 24 30 28 24 27 34
(Answer: 𝐻1 : 𝜎𝐽2 ≠ 𝜎𝐹2 , critical value = 4.90, test statistic = 5.30, reject 𝐻0 )

23. A researcher claims that the variation in the salaries of elementary school teachers is greater than
the variation in the salaries of secondary school teachers. A sample of the salaries of 30 elementary
school teacher has a variance of RM8324, and a sample of the salaries of 30 secondary school
teachers has a variance of RM2862. At 𝛼 = 0.05, can the researcher conclude that the variation in
the elementary school teachers’ salaries is greater than the variation in the secondary school
teachers’ salaries?

5
STA408 Tutorial 3 Chapter 3: Hypothesis Testing

(Answer: 𝐻1 : 𝜎𝐸2 > 𝜎𝑆2 , critical value = 1.65, test statistic = 2.91, reject 𝐻0 )

24. In the hospital, the standard deviation of the noise levels of the 11 intensive care units and 25 non-
medical care areas, such as kitchens, machine rooms are as given in the Minitab output below.
Assume that the variables are normally distributed.

Test and CI for Two Variances

Method

Null hypothesis Variance(First) / Variance(Second) = 1

Alternative hypothesis Variance(First) / Variance(Second) ≠ 1
Significance level α = 0.1
F method was used. This method is accurate for normal data only.
Statistics
90% CI for
Sample N StDev Variance Variances
First 11 4.100 16.810 ( 9.182, 42.662)
Second 25 13.200 174.240 (114.836, 301.966)
Ratio of standard deviations = 0.311
Ratio of variances = 0.096
90% Confidence Intervals
CI for
CI for StDev Variance
Method Ratio Ratio
F (0.207, 0.514) (0.043, 0.264)
Tests
Test
Method DF1 DF2 Statistic P-Value
F 10 24 0.10 0.001
(a) Show that the 90% confidence interval for the variance of the first population is between
9.182 and 42.662.
(b) Verify the 90% confidence interval for the ratio of the two population variances as given in
the output above.
(c) At 𝛼 = 0.10, is there a significant difference between the standard deviations of these two
areas? (Answer: 𝐻1 : 𝜎𝐹2 ≠ 𝜎𝑆2 , 𝑝-value = 0.001 < 𝛼 = 0.10, reject 𝐻0 )

Miscellaneous Questions
25. The Minitab output below shows the analysis of the prices (in RM) for Light Tuna in Water and
Light Tuna in Oil of a particular brand.
Two-Sample T-Test and CI: Light Tuna in Water, Light Tuna in Oil

Two-sample T for Light Tuna in Water vs Light Tuna in Oil

N Mean StDev SE Mean

Light Tuna in Water 14 0.901 0.414 0.11
Light Tuna in Oil 11 1.147 0.679 0.20

Difference = μ (Light Tuna in Water) - μ (Light Tuna in Oil)

Estimate for difference: -0.246
98% CI for difference: (-0.795, 0.303)
T-Test of difference = 0 (vs ≠): T-Value = -1.12 P-Value = 0.274 DF = 23
Both use Pooled StDev = 0.5448

(a) Based on the output, what is the assumption of variances for the two populations? (𝜎𝑊 2
= 𝜎𝑂2 )
(b) Test if there is a significance difference between the population means of the prices (in RM)
for Tuna in Water and Light Tuna in Oil of the brand. Use 𝛼 = 0.02. (Do not reject 𝐻0 )

6
STA408 Tutorial 3 Chapter 3: Hypothesis Testing

(c) State the 98% confidence interval for the difference in the mean prices (in RM) of Light Tuna
in Water and Light Tuna in Oil for the brand. Is the confidence interval consistent the
conclusion in (b)? Justify your answer. (Yes, they are consistent because the value of 0 is
in the interval.)

26. Determine if each of the following statement is TRUE or FALSE.

(a) The probability of Type I error is denoted by 𝛼, significance level.
(b) 𝜒 2 distribution is used to test hypothesis for ratio between two population variances.
(c) The point estimate for paired differences is denoted by 𝑑̅.
(d) The point estimate for the difference in two population means is 𝜇1 − 𝜇2 .
(e) The degrees of freedom used to find the critical value(s) for the hypothesis test of paired
differences is 𝑛 − 1, where 𝑛 is the sample size.
(f) Pooled standard deviation is used to calculate the standard error for difference in two
population means when the population variances are unknown but equal.
(g) The null hypothesis for a right-tailed test is rejected if 𝑝-value > 𝛼.
(h) A Type I error occurs when a true null hypothesis is rejected.
𝛼
(i) The null hypothesis of a two-tailed test is rejected if p-value < .
2
(Answer: (a) TRUE (b) FALSE (c) TRUE (d) FALSE (e) FALSE (f) TRUE (g) FALSE (h) TRUE
(i) FALSE)

27. A company sent seven employees to attend a course in building self-confidence to evaluate whether
the course is effective in increasing the employees’ self-confidence. The Minitab output below
shows the analysis of the scores of the employees before and after the course.
Paired T-Test and CI: Before, After

Paired T for Before - After

N Mean StDev SE Mean

Before 7 6.571 2.070 0.782
After 7 8.000 2.160 0.816
Difference 7 -1.429 1.988 0.751

95% upper bound for mean difference: 0.032

T-Value = -1.90 P-Value = 0.053
(a) Show that the test statistic for the paired differences is −1.90.
(b) Test at 5% significance level whether attending the course increases the mean score of
employees. State the hypotheses clearly. (Do not reject 𝐻0 )

28. A group of researchers claimed that the number of calories in 85 grams of French fries is not 250.
A random sample of 41 popular fast-food restaurants were selected to gain the information on the
number of calories in 85 grams of French fries. Below is the Minitab output of the data collected.
One-Sample T: calories

Test of mu = 250 vs  250

Variable N Mean StDev SE Mean T P

calories 41 252.925 33.053 5.162 0.57 0.285
Assume that the number of calories in 85 grams of French fries is normally distributed.
(a) Show that the test statistic is 0.57.
(b) State the null and alternative hypotheses for the study above.
(c) By using the p-value, can we conclude the researchers’ claim at 𝛼 = 0.10?

7
STA408 Tutorial 3 Chapter 3: Hypothesis Testing

(d) Construct a 90% confidence interval for the mean number of calories in all 85 grams of
French fries. Is the confidence interval consistent with your conclusion in part (c)? Support
your answer.
(Answer: (244.232, 261.618); Yes, because the value of 250 is in the interval)

29. Trace metals in drinking water affect the flavour and an unusually high concentration can pose a
health hazard. Ten pairs of data were taken measuring zinc concentration in bottom water and
surface water. Does the data suggest that the true average concentration in the bottom water
exceeds that of surface water? Use 𝛼 = 0.01.
Paired T-Test and CI: Bottom, Surface
Paired T for Bottom - Surface
N Mean StDev SE Mean
Bottom 10 0.5649 0.1468 0.0464
Surface 10 0.4845 0.1312 0.0415
Difference 10 0.0804 0.0523 0.0165
99% lower bound for mean difference: 0.0338
T-Test of mean difference = 0 (vs > 0): T-Value = 4.86 P-Value = 0.000

30. In a packing plant, a machine packs cartons with jars. It is supposed that a new machine will pack
faster on the average than the machine currently used. The Minitab output below displays the
statistics for the data for the two samples.
Statistics
N Mean StDev SE Mean
New Machine 10 42.140 0.683 0.22
Old Machine 10 43.230 0.750 0.24
The Minitab output for the test and confidence interval for two variances for the new and old
machines is as follows.
Test and CI for Two Variances: New Machine, Old Machine
Method
Null hypothesis σ(New Machine) / σ(Old Machine) = 1
Alternative hypothesis σ(New Machine) / σ(Old Machine) ≠ 1
F method was used. This method is accurate for normal data only.
Statistics
95% CI for
Variable N StDev Variance StDevs
New Machine 10 0.683 0.467 (0.470, 1.248)
Old Machine 10 0.750 0.562 (0.516, 1.369)
Tests
Test
Method DF1 DF2 Statistic P-Value
F 9 9 0.83 0.787
Assume that both the samples were drawn from normal distributions.
(a) Show that the pooled standard deviation for the two samples is 0.717.
(b) At 5% significance level, can we conclude that the population variances of the new machine
and the old machine are different? 𝜎12 = 𝜎22
(c) Based on your conclusion in (b), is there a significant difference between the population
means of the new machine and the old machine? Use 𝛼 = 0.05.
(From (b), 𝜎12 = 𝜎22 assumed; critical values = ±2.101; test statistic = −3.399; reject 𝐻0 )

31. The Minitab output below shows the analysis of the ceramic strength measurements for two
batches of materials.
Test for Two Variances: Batch I, Batch II
Statistics

8
STA408 Tutorial 3 Chapter 3: Hypothesis Testing

N Mean StDev SE Mean

Batch I 17 16.18 2.48 0.60
Batch II 15 24.67 4.67 1.2
Tests
Test
Method DF1 DF2 Statistic P-Value
F 16 14 0.28 0.018
(a) Test the null hypothesis at 1% significance level whether the population variances of the
ceramic strength measurement for the two batches of materials are equal.
(𝐻1 : 𝜎𝐼2 ≠ 𝜎𝐼𝐼2 , 𝑝-value = 0.018, do not reject 𝐻0 )
(b) Based on the conclusion in (a), is there enough evidence to conclude that the population
mean for Batch II is greater than the population mean for Batch I at 𝛼 = 0.01?
(From (a), 𝜎𝐼2 = 𝜎𝐼𝐼2 , 𝐻1 : 𝜇𝐼𝐼 > 𝜇𝐼 or 𝐻1 : 𝜇𝐼𝐼 − 𝜇𝐼 > 0, critical value = 2.457, 𝑠𝑝 = 3.6685,
test statistic = 6.533, reject 𝐻0 )

32. A certain chemical pollutant in the Klang River has been constant for several years with mean
𝜇 = 34 ppm (parts per million) and standard deviation 𝜎 = 8 ppm. A group of factory
representatives whose companies discharge liquids into the river recently claimed that they have
lowered the average of the pollutant with improved filtration devices. A group of environmentalists
then collected a sample of size 61 which gave a mean of 32.3 ppm with standard deviation 7.5 ppm.
(a) Is there sufficient evidence at 5% significance level for the group of environmentalists to
support the factory representatives’ claim?
(𝐻1 : 𝜇 < 34, critical value  1.6449, test statistic  1.6597, reject 𝐻0 )
(b) Test at 2% significance level if there is a change in the population standard deviation of the
chemical pollutant?
(𝐻1 : 𝜎 ≠ 8, critical values  37.485, 88.379, test statistic  52.734, do not reject 𝐻0 )

33. Hydrocarbon emissions from cars are known to have decreased dramatically during the 1980s. A
study was conducted to compare the hydrocarbon emissions at idling speed, in parts per million
(ppm), for automobiles from 1980 and 1990. Thirteen cars of each model year were randomly
selected and their hydrocarbon emission levels were recorded. The Minitab output of two sample
t-test for the study above is as follows.
Two-Sample T-Test and CI: 1980, 1990
Two-sample T for 1980 vs 1990
N Mean StDev SE Mean
1980 13 453 328 91
1990 13 142 104 29

Difference = μ (1980) - μ (1990)

Estimate for difference: 311.2
95% lower bound for difference: 143.1
T-Test of difference = 0 (vs >): T-Value = 3.26
Assume both the populations are normally distributed.
(a) Test at 5% significance level whether there is a difference in the population variances of the
hydrocarbon emissions at idling speed in ppm for automobiles from 1980 and 1990.
(𝐻1 : 𝜎12 ≠ 𝜎22 , critical value  3.28, test statistc  9.95, reject 𝐻0 )
(b) From the conclusion in part (a), can we conclude that the mean hydrocarbon emissions at
idling speed in ppm for all automobiles have decreased from 1980 and 1990? Use 𝛼 = 0.05.
(From (a) 𝜎12 ≠ 𝜎22 , 𝐻1 : 𝜇1 > 𝜇2 , 𝑣 = 14, critical value = 1.761, test statistic = 3.26, reject 𝐻0 .)

34. There is reason to believe that drying seeds before planting will increase plant yield. Hence, seeding
eleven different plots of land with two different types of seed: regular and kiln-dried was carried
out and the resulting pairs of data (corn yield in gram per square meter) are as follows.
Regular 213 217 214 280 236 220 231 162 181 148 169

9
STA408 Tutorial 3 Chapter 3: Hypothesis Testing

Kiln-dried 225 215 225 276 244 216 238 166 173 162 172
Assume the population of the corn yield is normally distributed. Do the data suggest that the true
average corn yield (in gram per square meter) increased after drying the seeds before planting at
5% significance level?
(𝐻1 : 𝜇𝑅 − 𝜇𝐾 < 0 or 𝜇𝑑 < 0, critical value = −1.812, test statistic = −1.6726, do not reject 𝐻0 .)

35. In order to investigate the relationship between mean job tenure in years among workers who have
a bachelor’s degree or higher and those who do not, random samples of each type of worker were
taken, with the following results together with a Minitab output.
Sample size Sample mean Sample standard deviation
Bachelor’s degree or higher 30 5.2 1.3
No degree 32 5.0 1.5
Test and CI for Two Variances
Method
Null hypothesis σ(First) / σ(Second) = 1
Alternative hypothesis σ(First) / σ(Second) ≠ 1
Statistics
98% CI for
Sample N StDev Variance StDevs
First 30 1.300 1.690 (0.994, 1.854)
Second 32 1.500 2.250 (1.156, 2.111)
Tests
Test
Method DF1 DF2 Statistic P-Value
F 29 31 0.75 0.441
(a) Test at 2% significance level whether there is a difference between the population variances
of the job tenure in years among workers who have a bachelor’s degree or higher and those
who do not.
(b) From the conclusion in part (a), can we conclude a significant difference between the mean
job tenure in years among workers who have a bachelor’s degree or higher and those who do
not? Use 𝛼 = 0.02.

36. Engineers at a tire manufacturing corporation wish to test a new tire material for increased
durability. To test the tires under realistic road condition, new front tires are mounted on each of
eleven company cars, one tire made with a production material and the other with the experimental
material. After a fixed period the eleven pairs were measured for wear. The amount of wear for each
tire (in mm) is shown in the table below.
Production 5.1 6.5 3.6 3.5 5.7 5.0 6.4 4.7 3.2 3.5 6.4
Experimental 5.0 6.5 3.1 3.7 4.5 4.1 5.3 2.6 3.0 3.5 5.1
Assume that the distribution of wear is normally distributed, test whether the mean wear with the
experimental material is less than that for the production material at 5% significance level?

37. A researcher claims that the BMI of a certain population is less than 35 on average. The Minitab
output below summarises the statistics of a random sample of 14 people.
One-Sample T: BMI
Variable N Mean StDev SE Mean T P
BMI 14 31.21 10.58 2.83 -1.34 0.102
Assume that the population distribution of BMI is normally distribution.
(a) Show that the test statistic is 1.34.
(b) Test the researcher’s claim at 10% significance level.

38. It is claimed that a new diet will reduce a person’s weight (in kilograms) on average in a period of

10
STA408 Tutorial 3 Chapter 3: Hypothesis Testing

2 weeks. The weights of seven women who followed this diet were recorded before and after the
2-week period.
Weight before 58.5 60.3 61.7 62.1 64.0 62.6 54.7
Weight after 60.0 54.9 58.1 63.0 58.5 59.9 56.4
Assume that the distribution of weights is normally distributed, can you conclude that the mean
weight of the seven women reduced after the 2-week period at 5% significance level?

39. A study was conducted by the Department of Zoology to determine if there is a significant
difference in the density of organisms at two different stations of a drainage basin. The summarised
data of the number of organisms per square meter at the two stations together with the Minitab
output are as given below.
Sample size Sample mean Sample variance
Station A 16 9898 62005060
Station B 12 4121 6147936

Test and CI for Two Variances: Station A, Station B

Method
Null hypothesis Variance(Station A) / Variance(Station B) = 1
Alternative hypothesis Variance(Station A) / Variance(Station B) ≠ 1
F method was used. This method is accurate for normal data only.
Tests
Test
Method DF1 DF2 Statistic P-Value
F 15 11 10.09 0.000
Assume that the population distribution for the density of organisms at the two stations are
normally distributed.
(a) Test at 1% significance level whether there is a difference in the population variances for the
density of the organisms at the two stations of the drainage basin.
(b) From the conclusion in (a), what is the assumption of variances in this study?
(c) Based on your answers in (a) and (b), show that the degrees of freedom for testing the
difference in the population means for the density of the organisms at the two stations is 18.
(d) Is there a significant difference in the density of organisms at the two stations at 𝛼 = 0.01?
(Hint: Consider the results in (a), (b) and (c)).

40. The Minitab output below shows the analysis of a study involving two independent samples. By
assuming that the populations from which the samples were taken are normally distributed,
answer the questions below based on the output.
Two-Sample T-Test and CI
Sample N Mean StDev SE Mean
1 12 10.94 1.26 0.36
2 16 12.15 1.99 0.50
Difference = μ (1) - μ (2)
Estimate for difference: -1.210
95% CI for difference: (-2.560, 0.140)
T-Test of difference = 0 (vs ≠): T-Value = A P-Value = 0.077 DF = B
Both use Pooled StDev = 1.7194
(a) Find the missing values of A and B in the above output.
(b) What is the assumption of variances used in the hypothesis test? Justify your answer.
(c) Can you conclude a difference in the two population means at 𝛼 = 0.05?
(d) State the 95% confidence interval for 𝜇1 − 𝜇2 . Does the interval support your conclusion in
(c)? Explain your answer.

11
STA408 Tutorial 3 Chapter 3: Hypothesis Testing

12