Seminar 3

Question1 (Chapter 9: one-tail test, form of hypothesis, mean)

The owner of a local nightclub has recently surveyed a random sample of n =
250 customers of the club. She would now like to determine whether or not
the mean age of her customers is greater than 30. If so, she plans to alter the
entertainment to appeal to an older crowd. If not, no entertainment changes
will be made.
1.1 The appropriate hypotheses to test are
Answer: H0 : 30 versus H1 : > 30.
1.2 Using the sample information provided, calculate the value of the test
statistic.
Answer:
t = (30 30.45) / (5 / SQRT(250)= -1.42
1.3 Suppose she found that the sample mean was 30.45 years, and the
sample standard deviation was 5 years. If she wants to have a level of
significance at 0.01. (One-tail test)
Answer :
Reject H0 if t > 2.3263 (use the table E.3)
1.4 Suppose the test statistic does fall in the rejection region at = 0.05. what
decision should she make?
Answer :
Do not reject H0. because t statistics < 2.3263
Question 2 (Chapter 9: one-tail test, proportion, form of hypothesis)
A major Blu-ray rental chain is considering opening a new store in an area
that currently does not have any such stores. The chain will open if there is
evidence that more than 5,000 of the 20,000 households in the area are
equipped with Blu-ray players. It conducts a telephone poll of 300 randomly
selected households in the area and finds that 96 have Blu-ray players.
1|Page

2.1 State the test of the hypothesis that is of interest to the rental chain.
Answer:
Propotion =5000/20000=0.25
H0 : 0.25 versus H1 : > 0.25
2.2 The value of the test statistic in this problem is approximately equal to
Answer: 2.8

2.3 Given the level of significant = 0.05, the p-value associated with the test
statistic in this problem is approximately equal to
Answer: 0.0026

Note: Probability of Z=2.8 from the table E.2 = 0.9974 then p-value = 1-0.9974 =
0.0026
2.4 The rental chain's conclusion from the hypothesis test using a 5% level of
significance is____. Why?
Answer :
The rental chain's conclusion is to open a new store because P-value of Z=
2.8(0.0026) is less than 0.05 then reject H0 in favor of H1.
Question3 (Chapter 10: pooled variance, t test, difference between two
means)

2|Page

Are Japanese managers more motivated than American managers? A

randomly selected group of each were administered the Sarnoff Survey of
Attitudes Toward Life (SSATL), which measures motivation for upward mobility.
The SSATL scores are summarized below. Given the level of significance at
0.05.
American Japanese
Sample Size
211
100
Sample Mean SSATL
Score
65.75
79.83
Sample Std. Dev.
11.07
6.41

3.1 Referring to table above, the researcher was attempting examine

whether the Japanese managers are more motivated than American
managers. What is an appropriate alternative hypothesis?
Answer:
H1: Japanese > American
3.2 From the analysis in table above, the correct test statistic is
Answer: -11.76

3.3 The proper conclusion for this test is

Answer:
3|Page

At the = 0.05 level, the p-value (6.150883E-27) is lower than 0.05. The proper
conclusion is this evidence indicates that Japanese managers are more
motivated than American managers. (Reject the null hypothesis)

Question 4 (Chapter 10: Z test, difference between two proportions, form of

hypothesis)
The Wall Street Journal recently published an article indicating differences in
perception of sexual harassment on the job between men and women. The
article claimed that women perceived the problem to be much more
prevalent than did men. One question asked of both men and women was:
"Do you think sexual harassment is a major problem in the American
workplace?" 24% of the men compared to 62% of the women responded
"Yes." Assuming W designates women's responses and M designates men's,
4.1what hypothesis should The Wall Street Journal test in order to show that its
claim is true?
Answer:
H0 : W - M 0 versus H1 : W - M > 0
4.2 Suppose that 150 women and 200 men were interviewed. What is the
value of the test statistic?
Answer: 7.173 (see more details in the table below)
4.3 Suppose that 150 women and 200 men were interviewed. For a 0.01 level
of significance, what is the critical value for the rejection region?
Answer: 2.33 (see more details in the table below)
4.4 Construct a 99% confidence interval estimate of the difference between
the proportion of women and men who think sexual harassment is a major
problem in the American workplace.
Answer: 0.25 to 0.51 (see more details in the table below)
4.5 Construct a 95% confidence interval estimate of the difference between
the proportion of women and men who think sexual harassment is a major
problem in the American workplace.
Answer: 0.28 to 0.48

4|Page

Question 5 (Chapter 11: One way ANOVA, Mean squares in One way
ANOVA, F statistics, Tukey-Kramer procedure)
5.1 In a one-way ANOVA, if the computed F statistic exceeds the critical F
value. What decision should you make?
Answer :
The computed F statistic (exceeded the critical F value) falls into the
region of rejection. Then, reject H0 since there is evidence of a
treatment effect.
5.2 Why would you use the Tukey-Kramer procedure?
Answer: Tukey-Kramer procedure can be used for making comparisons
between all pairs of groups or testing differences in pairwise means.
5.3 How to calculate the F test statistic in a one-way ANOVA?
Answer:

F test statistic =
Or

F test statistic =

5|Page

5.4 How to calculate the degrees of freedom for the F test in a one-way
ANOVA?
Answer:

Among group : (c - 1)
Within Group: (n - c)
Total : (n - 1)

Question 6 (Chapter 11: Analysis of variance summary table page 423)

A research company wants to compare the mean sales-to-appraisal ratios of
residential properties sold in four neighborhoods (G1, G2, G3, and G4). Four
properties are randomly selected from each neighborhood and the ratios
recorded for each, as shown below.
G1 1.2, 1.1, 0.9, 0.4
G3: 2.5, 2.1, 1.9, 1.6

G2: 1.0, 1.5, 1.1, 1.3

G4 : 0.8, 1.3, 1.1, 0.7

Interpret the results of the analysis summarized in the following table (Hint:
Table11.1 page 423):

Source
Neighborhoods
Error
Total

df

SS
3.1819

MS
1.0606

F
10.76

P-value
0.001

12
4.3644

6.1 Referring to table above, the among group degrees of freedom is

Answer: 3
6.2 Referring to table above, the within group sum of squares is
Answer: 4.3644-3.1819=1.1825
6.3 Referring to table above, the within group mean squares is
Answer: 1.1825/12 = 0.98542
6.4 At the 0.05 level of significance, what conclusion can you make?
Answer: P-value (0.001) is less than the significance level (0.05), and then null
hypothesis is rejected. You can conclude that: The mean ratios for the 4
neighborhoods are not all the same.

6|Page

Question 7 (Chapter 13 : Regression)

7. 1 What is Y-intercept (b0)? Or what does it represent?
Answer :
Y-intercept (b0)is the predicted value of Y when X = 0, or it represents the
estimated average Y when X = 0.
7.2 The managers of a brokerage firm are interested in finding out if the
number of new clients a broker brings into the firm affects the sales
generated by the broker. They sample 12 brokers and determine the number
of new clients they have enrolled in the last year and their sales amounts in
thousands of dollars. These data are presented in the table that follows.
Broker
1
2
3
4
5
6
7
8
9
10
11
12

Clients
27
11
42
33
15
15
25
36
28
30
17
22

Sales
52
37
64
55
29
34
58
59
44
48
31
38

Referring to the table, what is the estimated slope parameter for the sales
generated by the broker?
Answer : slope parameter for the sales generated by the broker = 1.1186 (
Topics: Section 13.2)
The link below is the quick guide of how to run regression with MS-Excel
https://faculty.fuqua.duke.edu/~pecklund/ExcelReview/Use%20Excel%20200
7%20Regression.pdf

7|Page

7.3 Referring to the table, what is the estimated average change in the sales
if client goes up by 1.00?
Answer : Yi = 17.6919+1.1186 X1
If client goes up by 1.00, the estimated average change in the sales will be
1.1186.
7.4 Referring to the table, what is the coefficient of correlation for these
data?

8|Page

Answer :
r = + 0.886 if b1 > 0
r = - 0.886 if b1 < 0
b1 = 1.1186 ; b1>0 then r = 0.886
(More detail on page 530)
7.5 Referring to the table, what percentage of the total variation in sales is
explained by clients?

Topics: Section 13.3

Answer : percentage of the total variation in sales is explained by clients is R
square , it equals to 78.46%. For multiple regression, the total variation
explained is Adjusted R square (Coefficient of multiple determination; see
more details in section 14.2) .
7.6 Referring to the table, what is the standard error of the estimate, SYX, for
the data? (Formula is on page 516)
Answer : Formula is on page 516
Then
SYX =5.804

9|Page

7.7 Referring to the table, what is the standard error of the regression slope
estimate, Sb1?
Answer:
The standard error of the regression slope estimate(Sb )= 20.197

7.8 How to measure the variation in Regression? (Hint: See more details on
page 514)
Answer:

10 | P a g e

Measures of variation in Regression can compute from

SST= SSR+SSE
SST= 1227.38 + 336.869= 1564.25
(See more details on page 514)
Question 8 (Chapter 14: r-square, adjust r-square)
8.1 In a multiple regression, what is the coefficient of multiple determination?
What is the value of the coefficient of multiple determination? How to
interpret this value?
Topics: Section 14.2
Answer :

The coefficient of multiple determination represents the proportion of

the variation in Y that is explained by the set of individual variables (Set
of X; X1, X2, Xn )

The value of the coefficient of multiple determination has to fall

between 0 and +1.

2 =

If = 0.78 ,interpretation should be :

The coefficient of multiple determination indicated that 78% of the
variation in Y (e.g., Sales) is explained by the variation in the set of X
(e.g., price, promotional expenditures).

8.2 What are the differences between R-squared and Adjusted R-squared?
Topics: Section 14.2
Answer :
R-squared assumes that every X (independent variables) in the model helps
to explain variation in Y (Dependent variable). So, it gives us a percentage of
variation in Y that can be explained by our prediction equation (set of Xs).
Adjusted R-squared tells you the percentage of variation explained by only
those Xs (Independent variables; only those IVs that pass the t-test) that truly
affect Y (Dependent variable). Only that it takes into account both sample
(1)
size and the number of IV's (formula: Adjusted R-squared =1-((1- 2 )
)).
(1)

11 | P a g e

With a sufficiently large sample size and a sufficiently small number of IV's, our
Adjusted R-squared and R-squared will be nearly equal. But when sample size
is small and/or there are a large number of IV's, the Adjusted R-squared will
be smaller. To penalizes you for adding independent variable(s) that do not
belong in the model. So, you can expect that the value of the Adjusted Rsquared will be less than or equal to value of R-squared.
(See more details
http://www.bus.ucf.edu/faculty/rhofler/file.axd?file=2012%2F2%2FR2+vs+adj+
R2.pdf)

12 | P a g e