Exam

Name___________________________________

TRUE/FALSE. Write 'T' if the statement is true and 'F' if the statement is false.

1) True or False: When the F test is used for ANOVA, the rejection region is always in the right tail. 1)

2) True or False: If you are comparing the mean sales among 3 different brands, you are dealing with 2)
a three-way ANOVA design.

MULTIPLE CHOICE. Choose the one alternative that best completes the statement or answers the question.

3) The F test statistic in a one-way ANOVA is 3)

A) MSA/MSW. B) SSA/SSW. C) MSW/MSA. D) SSW/SSA.

4) The degrees of freedom for the F test in a one-way ANOVA are 4)

A) (c - 1) and (n - c). B) (c - n) and (n - 1).
C) (n - 1) and (c - n). D) (n - c) and (c - 1).

5) In a one-way ANOVA, the null hypothesis is always 5)

A) some of the population means are different.
B) there is some treatment effect.
C) all the population means are different.
D) there is no difference in the population means.

6) In a one-way ANOVA, if the computed F statistic is greater than the critical F value you may 6)
A) not reject H0 since there is no evidence of a difference in the means.
B) reject H0 since there is evidence all the means differ.
C) reject H0 since there is evidence that not all the means are different.
D) not reject H0 because a mistake has been made.

7) Which of the following components in an ANOVA table are not additive? 7)

A) Degrees of freedom B) Sum of squares
C) Mean squares D) It is not possible to tell.

8) When would you use the Tukey-Kramer procedure? 8)

A) to test for differences in pairs of means B) to test independence of errors
C) to test for homogeneity of variance D) to test for normality

1
An airline wants to select a computer software package for its reservation system. Four software packages (1, 2, 3, and 4) are
commercially available. The airline will choose the package that bumps as few passengers as possible during a month. An
experiment is set up in which each package is used to make reservations for 5 randomly selected weeks. (A total of 20 weeks
was included in the experiment.) The number of passengers bumped each week is obtained, which gives rise to the following
Excel output:

ANOVA
Source of Variation SS df MS F P-value F crit
Between Groups 212.4 3 8.304985 0.001474 3.238867
Within Groups 136.4 8.525

Total 348.8

9) The within groups degrees of freedom is 9)

A) 16. B) 4. C) 19. D) 3.

10) The total degrees of freedom is 10)

A) 4. B) 16. C) 19. D) 3.

11) The among-group (between-group) mean squares is 11)

A) 8.525. B) 70.8. C) 637.2. D) 212.4.

12) At a significance level of 1%, 12)

A) there is insufficient evidence to conclude that the mean number of customers bumped by the
4 packages are not all the same.
B) there is sufficient evidence to conclude that the mean number of customers bumped by the 4
packages are not all the same.
C) there is insufficient evidence to conclude that the mean number of customers bumped by the
4 packages are all the same.
D) there is sufficient evidence to conclude that the mean number of customers bumped by the 4
packages are all the same.

ESSAY. Write your answer in the space provided or on a separate sheet of paper.

As part of an evaluation program, a sporting goods retailer wanted to compare the downhill coasting speeds of 4 brands of
bicycles. She took 3 of each brand and determined their maximum downhill speeds. The results are presented in miles per
hour in the table below.

Trial Barth Tornado Reiser Shaw

1 43 37 41 43
2 46 38 45 45
3 43 39 42 46

13) Construct the ANOVA table from the sample data.

SHORT ANSWER. Write the word or phrase that best completes each statement or answers the question.

14) The null hypothesis that the mean downhill coasting speeds of the 4 brands of bicycles are 14)
equal will be rejected at a level of significance of 0.05 if the value of the test statistic is
greater than ________.

2
TRUE/FALSE. Write 'T' if the statement is true and 'F' if the statement is false.

15) True or False: The null hypothesis should be rejected at a 5% level of significance. 15)

16) True or False: The decision made implies that all 4 means are significantly different. 16)

17) True or False: The test is valid only if the population of speeds has the same variance for the 4 17)
brands.

18) True or False: The test is less sensitive to the assumption that the population of speeds has the same 18)
variance for the 4 brands because the sample sizes of the 4 brands are equal.

19) True or False: The test is valid only if the population of speeds is normally distributed. 19)

20) True or False: The test is robust to the violation of the assumption that the population of speeds is 20)
normally distributed.

SHORT ANSWER. Write the word or phrase that best completes each statement or answers the question.

21) Using an overall level of significance of 0.05, the critical value of the Studentized range Q 21)
used in calculating the critical range for the Tukey-Kramer procedure is ________.

22) Using an overall level of significance of 0.05, the critical range for the Tukey-Kramer 22)
procedure is ________.

TRUE/FALSE. Write 'T' if the statement is true and 'F' if the statement is false.

23) True or False: Based on the Tukey-Kramer procedure with an overall level of significance of 0.05, 23)
the retailer would decide that there is no significant difference between any pair of mean speeds.

MULTIPLE CHOICE. Choose the one alternative that best completes the statement or answers the question.

24) The null hypothesis for Levene's test for homogeneity of variances is 24)

A) H0 : A = B = C = D. B) H0 : µA = µB = µC = µD.

2 2 2 2
C) H0 : A= B= C = D. D) H0 : MA = MB = MC = MD.

SHORT ANSWER. Write the word or phrase that best completes each statement or answers the question.

25) What is the value of the test statistic for Levene's test for homogeneity of variances? 25)

26) What are the numerator and denominator degrees of freedom for Levene's test for 26)
homogeneity of variances respectively?

27) What is the critical value of Levene's test for homogeneity of variances at a 5% level of 27)
significance?

3
MULTIPLE CHOICE. Choose the one alternative that best completes the statement or answers the question.

28) What should be the decision for the Levene's test for homogeneity of variances at a 5% level of 28)
significance?
A) Reject the null hypothesis because the p-value is smaller than the level of significance.
B) Reject the null hypothesis because the p-value is larger than the level of significance.
C) Do not reject the null hypothesis because the p-value is larger than the level of significance.
D) Do not reject the null hypothesis because the p-value is smaller than the level of significance.

29) What should be the conclusion for the Levene's test for homogeneity of variances at a 5% level of 29)
significance?
A) There is sufficient evidence that the variances are not all the same.
B) There is insufficient evidence that the variances are not all the same.
C) There is sufficient evidence that the variances are all the same.
D) There is insufficient evidence that the variances are all the same.

Psychologists have found that people are generally reluctant to transmit bad news to their peers. This phenomenon has been
termed the "MUM effect." To investigate the cause of the MUM effect, 40 undergraduates at Duke University participated in
an experiment. Each subject was asked to administer an IQ test to another student and then provide the test taker with his or
her percentile score. Unknown to the subject, the test taker was a bogus student who was working with the researchers. The
experimenters manipulated two factors: subject visibility and success of test taker, each at two levels. Subject visibility was
either visible or not visible to the test taker. Success of the test taker was either top 20% or bottom 20%. Ten subjects were
randomly assigned to each of the 2 × 2 = 4 experimental conditions, then the time (in seconds) between the end of the test and
the delivery of the percentile score from the subject to the test taker was measured. (This variable is called the latency to
feedback.) The data were subjected to appropriate analyses with the following results.

Source df SS MS F PR > F
Suubject visibility 1 1380.24 1380.24 4.26 0.043
Test taker success 1 1325.16 1325.16 4.09 0.050
Interaction 1 3385.80 3385.80 10.45 0.002
Error 36 11,664.00 324.00
Total 39 17,755.20

30) What type of experimental design was employed in this study? 30)
A) 2 × 2 factorial design with 10 observations
B) completely randomized design with 4 treatments
C) randomized block design with four treatments and 10 blocks
D) None of the above

31) At the 0.01 level, what conclusions can you reach from the analysis? 31)
A) At the 0.01 level, the model is not useful for predicting latency to feedback.
B) At the 0.01 level, there is evidence to indicate that subject visibility and test taker success
interact.
C) At the 0.01 level, subject visibility and test taker success are significant predictors of latency
feedback.
D) At the 0.01 level, there is no evidence of interaction between subject visibility and test taker
success.

4
 32) In the context of this study, interpret the statement: "Subject visibility and test taker success 32)
interact."
A) The relationship between feedback time and subject visibility depends on the success of the
test taker.
B) The difference between the mean feedback time for visible and nonvisible subjects depends
on the success of the test taker.
C) The difference between the mean feedback time for test takers scoring in the top 20% and
bottom 20% depends on the visibility of the subject.
D) All of the above are correct interpretations.

A physician and president of a Tampa Health Maintenance Organization (HMO) are attempting to show the benefits of
managed health care to an insurance company. The physician believes that certain types of doctors are more cost-effective
than others. One theory is that Primary Specialty is an important factor in measuring the cost-effectiveness of physicians. To
investigate this, the president obtained independent random samples of 20 HMO physicians from each of 4 primary
specialties - General Practice (GP), Internal Medicine (IM), Pediatrics (PED), and Family Physicians (FP) - and recorded the
total charges per member per month for each. A second factor which the president believes influences total charges per
member per month is whether the doctor is a foreign or USA medical school graduate. The president theorizes that foreign
graduates will have higher mean charges than USA graduates. To investigate this, the president also collected data on 20
foreign medical school graduates in each of the 4 primary specialty types described above. So information on charges for 40
doctors (20 foreign and 20 USA medical school graduates) was obtained for each of the 4 specialties. The results for the
ANOVA are summarized in the following table.

Source df SS MS F PR > F
Specialty 3 22,855 7,618 60.94 0.0001
Med school 1 105 105 0.84 0.6744
Interaction 3 890 297 2.38 0.1348
Error 152 18,950
Total 159 42,800

33) What was the total number of doctors included in the study? 33)
A) 159 B) 20 C) 40 D) 160

34) What degrees of freedom should be used to determine the critical value of the F ratio against which 34)
to test for interaction between the two factors?
A) numerator df = 1, denominator df = 152 B) numerator df = 1, denominator df = 159
C) numerator df = 3, denominator df = 159 D) numerator df = 3, denominator df = 152

35) Interpret the test for interaction. 35)

A) There is insufficient evidence to say at the 0.10 level of significance that the difference
between the mean charges for foreign and USA graduates depends on primary specialty.
B) There is sufficient evidence to say at the 0.10 level of significance that mean charges depend
on both primary specialty and medical school.
C) There is sufficient evidence at the 0.10 level of significance of a difference between the mean
charges for foreign and USA medical graduates.
D) There is sufficient evidence to say at the 0.10 level of significance that the difference between
the mean charges for foreign and USA graduates depends on primary specialty.

5
36) Is there evidence of a difference between the mean charges of foreign and USA medical school 36)
graduates?
A) No, the test for the main effect for medical school is not significant at = 0.10.
B) Yes, the test for the main effect for primary specialty is significant at = 0.10.
C) Maybe, but we need information on the -estimates to fully answer the question.
D) No, the test for the interaction is not significant at = 0.10.

37) What assumption(s) need(s) to be made in order to conduct the test for differences between the 37)
mean charges of foreign and USA medical school graduates?
A) There is no significant interaction effect between the area of primary specialty and the
medical school on the doctors' mean charges.
B) The charges in each group of doctors sampled are drawn from populations with equal
variances.
C) The charges in each group of doctors sampled are drawn from normally distributed
populations.
D) All of the above are necessary assumptions.

6
Answer Key
Testname: CH11

1) TRUE
2) FALSE
3) A
4) A
5) D
6) C
7) C
8) A
9) A
10) C
11) B
12) B
13) Analysis of Variance
Source df SS MS F p
Bicycle Brands 3 81.33 27.11 10.17 0.004*
Error 8 21.33 2.67
Total 11 102.67

* or p < 0.005, tabular value

14) 4.07
15) TRUE
16) FALSE
17) TRUE
18) TRUE
19) TRUE
20) TRUE
21) 4.53
22) 4.27
23) FALSE
24) C
25) 0.1333
26) 3, 8
27) 4.07
28) C
29) B
30) A
31) B
32) D
33) D
34) D
35) A
36) A
37) D