Stat 1x1 Final Exam Review Questions (Units 13, 14, 15)

1. A hypothesis test for H0: µ = 10 vs. HA: µ > 10 resulted in a p-value of 0.0075.
TRUE or FALSE: The 99% confidence interval for  will include the value of 10.

2. A 90% confidence interval for  is given to be (10.25,12.5).

3. A 90% confidence interval for  is given to be (8.25,9.75).

4. A hypothesis test for H0: μ = 5 versus HA: μ < 5 resulted in a p-value of 0.08.
TRUE or FALSE: The 90% confidence interval will not include the hypothesized value of 5.

5. Suppose the respective 95% confidence intervals for μ1 and μ2 are (10, 15) and (5, 10).
TRUE or FALSE: If both sample sizes are equal, then the sample standard deviation for the first sample is
lower than the sample standard deviation of the second sample.

6. TRUE or FALSE: The t-distribution is like the Standard Normal distribution but has a larger variance.

7. An agricultural researcher plants 50 plots with a new variety of corn. A 95% C.I. for μ, the mean yield per
acre, is (146.71, 153.29).
TRUE or FALSE: The 90% confidence interval will be narrower.

8. A hypothesis test for one population mean from a sample of 5 ended up with a test-statistic of 2.10.
TRUE or FALSE: We reject the null hypothesis at a significance level of 0.05.

9. An agricultural researcher plants n plots with a new variety of corn. From a random sample of 45
observations, a 95% C.I. for μ (the mean yield per acre) is (146.71, 153.29).
TRUE or FALSE: The critical value for this confidence interval is 1.96.

10. Suppose the respective 95% confidence intervals for μ1 and μ2 are (8, 12) and (15, 21).
TRUE or FALSE: The difference between the sample means is 8.

11. A bar owner in Canada wanted to measure the monthly amount of alcohol customers purchased (by
individual receipts) and see if the amounts are changing from month to month. From k different months, she
randomly sampled the same number of receipts.
Source df SS MS F-Stat p-value
Treatments 2 346.50 173.25 21.00 0.0000
Error 198 1633.50 8.25
Total 200 1980.00

TRUE or FALSE: The bar owner sampled 67 receipts from each month in question.
12. A bar owner in Canada wanted to measure the monthly amount of alcohol customers purchased (by
individual receipts) and see if the amounts are changing from month to month. From k different months, she
randomly sampled the same number of receipts.
Source df SS MS F-Stat p-value
Treatments 5 1150 230 11.5 0.0000
Error 594 11880 20
Total 599 13030

TRUE or FALSE: The bar owner sampled from 5 different months.

13. A professor hypothesizes the average number of minutes student need to complete the Final Exam is less
than 130 minutes. A Type II error would occur if the professor concludes that the average exam time is
a. less than 130 minutes when, in reality, the average time is equal to 130 minutes.
b. more than 130 minutes when, in reality, the average time is less than 130 minutes.
c. not equal to 130 minutes when, in reality, the average time is less than 130 minutes.
d. equal to 130 minutes when, in reality, the average time is not equal to 130 minutes.
e. not less than 130 minutes when, in reality, the average time is less than 130 minutes.

14. A professor hypothesizes the average number of minutes student need to complete the Final Exam is less
than 130 minutes. A Type I error would occur if the professor concludes that the average exam time is
a. equal to 130 minutes when, in reality, the average time is less than 130 minutes.
b. not equal to 130 minutes when, in reality, the average time is less than 130 minutes.
c. less than 130 minutes when, in reality, the average time is equal to 130 minutes.
d. equal to 130 minutes when, in reality, the average time is not equal to 130 minutes.
e. less than 130 minutes when, in reality, the average time is less than 130 minutes.

15. In a recent study, a random sample of 61 patients with chronic lower back pain reported a sample mean
duration of back pain of 17.6 months with a sample standard deviation of 4.2 months.
In testing H0 : µ = 19 versus HA: µ ≠ 19, what is the appropriate conclusion to draw at the 1% and 2% levels of
significance?
a. Do not reject H0 at either the 1% or 2% levels of significance.
b. Reject H0 at both the 1% and 2% levels of significance.
c. Reject H0 at the 1% level of significance but not at the 2% level.
d. Reject H0 at the 2% level of significance but not at the 1% level.
e. There is not enough information to draw a conclusion at both the 1% and 2% levels of significance.

16. A hypothesis test for H0: µ = 0.125 vs. HA: µ < 0.125 from a sample of 5 ended up with a test-statistic of -2.10.
What is the p-value range?
a. Between 0.005 and 0.01.
b. Between 0.01 and 0.025.
c. Between 0.025 and 0.05.
d. Between 0.05 and 0.10.
e. Larger than 0.10.

17. A 90% confidence interval for a population mean based on a sample of n = 6 is (9.2, 18.8). What is the 95%
confidence interval for the population mean?
a. (7.88, 20.12)
b. (8.17, 19.83)
c. (7.95, 20.05)
d. (9.37, 18.63)
e. (8.28, 19.72)
 18. A researcher wants to estimate the mean cholesterol level of people in their city. A random sample of 21
people yields a sample mean cholesterol level of 224 mg/dL and a sample standard deviation of 24 mg/dL.
Assume cholesterol levels are approximately normally distributed. Construct a 95% confidence interval for
the population mean.
a. (221.62, 226.38)
b. (214.97, 233.03)
c. (213.74, 234.26)
d. (219.50, 228.50)
e. (213.08, 234.92)

Use the following information to answer the next two questions: Data from 16 automobile repairs yielded an
average of 24 minutes and a standard deviation of 2 minutes. The time of repairs follows a normal distribution.

19. Construct a 99% confidence interval for the mean repair time.
a. 24  (2.576)(0.500)
b. 24  (2.947)(0.500)
c. 24  (2.921)(0.500)
d. 24  (2.576)(0.125)
e. 24  (2.947)(0.125)

20. We test H0: µ = 23 vs. HA: µ ≠ 23. What decision is reached about H0?
a. The null hypothesis retained at level  = 0.10.
b. The null hypothesis rejected at level  = 0.05, but not at level  = 0.01.
c. The null hypothesis rejected at level  = 0.01, but not at level  = 0.05.
d. The null hypothesis rejected at level  = 0.10, but not at level  = 0.05.
e. The null hypothesis rejected at level  = 0.01.

21. In the years following the 2016 U.S. Presidential election it is hypothesized that Americans are drinking a lot
more alcohol than usual. As a master statistician, you wish to estimate the current mean daily amount of
money Americans spend on alcohol. Previous studies indicate daily amounts spent on alcohol has a standard
deviation of $4. Assume daily amounts spent on alcohol are approximately normally distributed. How many
Americans should you sample so there is a 98% chance your sample mean will be within $1 of the true
population mean?
a. 87
b. 44
c. 23
d. 10
e. 107
22. The Dean of the Business School at a university would like to test to see if a difference exists between the
average final exam grades for the Introduction to Marketing course and the Introduction to Finance course.
A random sample of eight students who took both courses was selected and their final exam grade
summaries are shown below.
Marketing Finance Difference
(Marketing - Finance)
Sample Size 8 8 8
Sample Mean 86.000 81.000 5.000
Sample S.D. 8.635 9.350 5.522

Note: If you decide the samples are independent use the Marketing and Finance summary statistics and do
not assume equal variances. If you decide the samples are dependent use the Difference summary statistics.
Assume all variables are approximately Normal.

Do the data provide sufficient evidence of a difference in grades between the two courses? What is the p-
value of the test?
a. Less than 0.02.
b. between 0.02 and 0.05
c. between 0.05 and 0.10
d. between 0.10 and 0.20
e. larger than 0.20

23. Ten students did poorly on their Math final exams in June. They then repeated the course in summer school
and rewrote their exam in August. The summary statistics of the two exams are given below.
June August Difference (August – June)
Sample Size 10 10 10
Sample Mean 62.17 65.5 3.33
Sample S.D. 6.61 7.78 5.10
Note: If you decide the samples are independent use the June and August summary statistics and do not
assume equal variability. If you decide the samples are dependent use the Difference summary statistics.
Assume all variables are approximately Normal.

Calculate the margin of error for the 98% confidence interval for the mean difference.
a. 8.24
b. 4.55
c. 3.75
d. 9.11
e. 4.12
24. A pilot study was carried out in 1991 at a hospital in Edmonton to compare two different methods of care
management of geriatric patients who were transferred from the emergency room to the geriatric ward. The
two methods were “usual care” and “geriatric team care.” The assignment of patients to the two groups was
done at random; 30 patients were assigned to the “usual care” group (control group) and 32 to the “geriatric
team care” group (treatment group). One of variables of interest was hospitalization costs (in dollars) for the
two different methods. An 80% confidence interval for the difference between mean hospitalization costs for
the two groups, μControl – μTreatment, was reported as 2198.3 ± 2199.4. If the confidence interval was
calculated assuming equal variances, what is the (approximate) value of the test statistic for testing
H0: μControl = μTreatment versus HA: μControl ≠ μTreatment?
a. 0.772
b. 1.000
c. 1.295
d. 1.670
e. 1.999

25. A researcher wishes to determine whether people with high blood pressure can reduce their blood pressure
by following a particular diet. Use the sample data below to construct a 99% confidence interval for μ1 – μ2
(control - treatment).
Control Group - Treatment Group - Difference
people with no diet (y1) people using diet (y2) (y1−y2)
Sample size 21 21 21
Sample mean 189.1 203.7 -14.60
Sample S.D. 38.7 39.2 55.08

a. (−39.7, 10.5)
b. (−48.8, 19.6)
c. (−34.8, 5.6)
d. (−35.3, 6.1)
e. (−47.1, 17.9)
26. A new postsurgical treatment was compared with a standard treatment. Seven subjects received the new
treatment, while seven others (the controls) received the standard treatment. The summary statistics of the
recovery times for the two treatments are given below.
New Treatment Group Standard Treatment Group Difference
(Standard – New)
Sample Size 7 7 7
Sample Mean 17.86 30.29 12.43
Sample S.D. 3.89 13.09 9.95
Note: If you decide the samples are independent use the New and Standard treatment summary statistics
and do not assume equal variances. If you decide the samples are dependent use the Difference summary
statistics. Assume all variables are approximately Normal.

Is there enough evidence to conclude that the recovery time for those receiving the new treatment is different
from the mean for those receiving the standard treatment? In performing this statistical test, the test-statistic
is found to be 2.408. What is the p-value range?
a. Less than 0.01.
b. Between 0.01 and 0.02.
c. Between 0.02 and 0.05.
d. Between 0.05 and 0.10.
e. Larger than 0.10.

27. A psychologist has developed a set of activities which she hopes will help children develop better reading
skills. In a study of the effectiveness of these activities, one class of second-grade children learns with the
activities. Another class of second-grade children serves as the control group and learned without the
activities. After some period, the reading skills of all these children were assessed. A summary of these data
is:
Activities class No activities class Difference
(Activities – No activities)
Sample Size 21 21 21
Sample Mean 51.48 41.52 9.96
Sample S.D. 9.01 7.15 12.36

Note: If you decide the samples are independent use the Activities and no Activities summary statistics and
assume equal variances. If you decide the samples are dependent use the Difference summary statistics.
Assume all variables are approximately Normal.

Calculate the margin of error for the 99% confidence interval for the mean difference.
a. 7.141
b. 6.787
c. 6.081
d. 7.305
e. 7.686
28. Does a football filled with helium travel farther than one filled with ordinary air? To answer this question,
two identical footballs (one filled with helium and one filled with ordinary air) were used in a study. Eleven
novice kickers were used to punt the footballs. A trial consisted of each punter kicking both footballs in a
random order. The kicker did not know which football (the helium-filled or the air-filled football) they were
kicking. The distance of each punt (in yards) was recorded, and the results are summarized in the following
table.
Helium-Filled Air-Filled Difference (Helium - Air)
Sample Size 11 11 11
Sample Mean 44.73 41.91 2.82
Sample S.D. 7.23 6.95 6.01
Note: If you decide the samples are independent, use the Helium-Filled and Air-Filled summary statistics and
assume equal variability. If you decide the samples are dependent, use the Difference summary statistics.
Assume all variables are approximately Normal.

What is the p-value of the test?

29. An education researcher is examining the differences in student performance on the final exam from 4
different sections of a first year Statistics class delivered using different teaching styles (conventional lecture
style, blended style, fully online). She collects random samples of 15 observations from each class to analyze.
In carrying out the test for any difference in means she found a test statistic to 4.25. Assume exam scores are
approximately normally distributed with the same population variance. Which of the following is the correct
p-value calculation?
a. 2P(t56  4.25)
b. P( F563  4.25)
c. P( F594  4.25)
d. P( F593  4.25)
e. 2 P( F563  4.25)
30. Some people believe most farms are huge, corporate-like enterprises covering thousands of acres. In
Canada, most of the country’s farms are small-scale, family-owned, and operated. Independent random
samples of farms were obtained from 6 Canadian provinces, with 9 observations in each group. The size (in
acres) was observed for each farm. Assume the sizes are approximately normally distributed. The following is
the ANOVA table of the data.
Source df SS MS F-Stat p-value
Treatments 0.0016

Error 4,250

Total 260,000

What is the F-test statistic?

31. Particulate is a serious form of air pollution often arising from industrial production. One way to reduce the
pollution is to put a filter at the end of the smokestack to trap the particulates. An experiment to determine
which smokestack filter design is best was run by placing four filters of different designs on an industrial
stack in random order. Each filter was tested 5 times. For each run, the same material was produced, and the
particulate emissions coming out of the filter were measured (in parts per billion) and are approximately
normally distributed. A partially completed ANOVA table of the data is given in the following.
Source df SS MS F-Stat p-value

Treatment 81.2 0.0000949

Error

Total 112.0

What is the best estimate of the common standard deviation?