Master of Business Administration Degree Online Examination

UNIVERSITY OF KELANIYA
Faculty of Commerce and Management Studies
2019/2020 Academic Year – Year 1 – Term II
Business Statistics MBA 52063/ 52063 (R)

Sunday 11th July 2021

No. of pages 09

Instructions to Candidates
1. Ensure that you adhere to the online examination guidelines.

2. This is an online open book examination. You may consult with any materials you wish.
However, you must ensure that you do not re-produce the same writings from the internet or
from any other source.

3. You will be given 2 and ½ hours to complete the examination (From 9.00 am to 11.30 am).

4. No. of questions: Five (05)

5. Answer any four (04) questions.

6. Please read all questions carefully and make sure you understand the facts before you begin
answering. Write legibly and be concise as possible.

1
Question No.01
(a) In fuel economy test in city driving conditions, a hybrid vehicle’s mean was 33.2 mpg with a
standard deviation of 3.2 mpg. A comparably sized gasoline vehicle’s mean was 22.2 mpg with a
standard deviation of 2.6 mpg. Which vehicle’s mpg was more consistent in relative terms?
(06 Marks)
(b)
(i) Briefly explain the four levels of measurement in data with an appropriate example for each.
(04 Marks)
(ii) Distinguish between “simple random sample” and “stratified sample” with an appropriate
example for each.
(03 Marks)
(c) Analysis of investment portfolio returns over a 20-year period showed the statistics below
Comparative Returns on Four Types of Investments
Investment Mean Return Standard Deviation Coefficient of
Variation
Venture funds (adjusted) 12.2 10.0 ?
All common stocks 10.6 10.0 ?
Real estate 7.5 12.4 ?
Treasury bills 5.7 0.9 ?

(i) Calculate and compare the coefficient of variation.

(ii) What do the data tells you about risk and return?
(07 Marks)
(d) Briefly explain the difference between descriptive statistics and inferential statistics.
(05 Marks)
(Total 25 Marks)

Question No.02
(a) The following contingency table shows average yield and average duration for 38 bond
funds.
Yield Average Portfolio Duration
Short (D1) Intermediate (D2) Long (D3) Total
Low (Y1) 16 4 0 20
Medium (Y2) 2 12 12 26
High (Y3) 4 8 18 30

2
 Total 22 24 30 76

For a randomly chosen bond fund, find the probability that,

i. The bond fund is of long duration
ii. The bond fund has high yield
iii. The bond fund has high yield given that it is of short duration
iv. The bond fund is of short duration given that it has high yield.
(10 Marks)
(b) Daily output of an oil refinery is normally distributed with a mean of 116,000 barrels of crude
oil per day with a standard deviation of 3500 barrels (You may use tables or Excel to calculate the
probabilities.)
i. What is the probability of producing at 116000 barrels?
ii. What is the probability of producing between 116000 barrels and 119500 barrels?
iii. What is the probability of producing less than 119500 barrels?
iv. What is the probability of producing less than 122500 barrels?
v. What is the probability of producing more than 112500 barrels?

(15 Marks)
(Total 25 Marks)

Question No.03
(a) The regression equation HomePrice = 102.6 + 5.2Income was estimated from a sample of 64
cities in the Western Province of Sri Lanka. Both variables are measured in thousands of rupees.
HomePrice is the median selling price of homes in the city and Income is median family income
for the city.
i. Interpret the slope.
ii. Is the intercept meaningful? Explain.
iii. Make a prediction of HomePrice when Income = Rs.100,000.
iv. Do you think that the above estimated regression equation is sufficient to explain the
variations in HomePrice?
(10 Marks)
(b) State whether the following statements are TRUE or FALSE;
i In regression, the dependent variable is referred to as the response variable.

3
ii. If a regression model's F test statistic is Fcalc = 43.82, we could say that the explained variance
is approximately 44 percent.
iii. Evans' Rule says that if n = 50 you need at least 5 predictors to have a good model.
iv. The model Y = β0 + β1X + β2X2 cannot be estimated by Excel because of the nonlinear term.
v. The random error term in a regression model reflects all factors omitted from the model.
(05 Marks)
(c)
i A multiple regression analysis with two independent variables yielded the following results in
the ANOVA table: SS(Total) = 798, SS(Regression) = 738, SS(Error) = 60. Calculate the R2.
ii. by inspecting the residuals of an estimated regression, what issues related to multiple
regression can be identified?
iii. What do you mean by Heteroscedasticity and Multicollinearity? Briefly explain
(10 Marks)
(Total 25 Marks)

Question No.04:
(a) “There are several parametric and non-parametric tests that can be chosen for analyzing
data in business and management-related quantitative research.”

Critically discuss the process of selecting an appropriate statistical test/s for business and
management research stating relevant criteria.

(09 Marks)

(b) If you are willing to apply each of the following parametric or non-parametric tests for
different research projects, fill in the following blanks in the given tables.

(i) Independent Samples t-Test

No. Item Answer / Description

1 Purpose of applying
Independent Samples t-test
2 Is it a parametric or non-
parametric statistical test?
3 Nature of samples

4
 4 The scale of measurement
of DV with an example
5 The scale of measurement
of IV with an example
6 Required no. of categories
in IV.
7 Required assumptions to
apply this statistical test.
8 State a practical example
for applying independent
samples t-test with null and
alternative hypotheses.

Where, IV = Independent Variable

DV= Dependent Variable

(ii) Kruskal Wallis H Test

No. Item Answer / Description

1 Purpose of applying
Kruskal Wallis H-test
2 Is it a parametric or non-
parametric statistical test?
3 Nature of samples
4 The scale of measurement
of DV with an example
5 The scale of measurement
of IV with an example
6 Required no. of categories
in IV.
7 Required assumptions to
apply this statistical test.
8 State a practical example
for applying the Kruskal
Wallis-H test with null and
alternative hypotheses.

5
(iii) Paired Sample t-test
No. Item Answer / Description
1 Purpose of applying Paired
Sample t-test
2 Is it a parametric or non-
parametric statistical test?
3 Nature of samples
4 The scale of measurement
of DV with an example
5 The scale of measurement
of IV with an example
6 Required no. of categories
in IV.
7 Required assumptions to
apply this statistical test.
8 State a practical example
for applying Paired Sample
t-test with null and
alternative hypotheses

(iv) Wilcoxon Sign Rank t-test

No. Item Answer / Description
1 Purpose of applying
Wilcoxon Sign Rank test
2 Is it a parametric or non-
parametric statistical test?
3 Nature of samples
4 The scale of measurement
of DV with an example
5 The scale of measurement
of IV with an example
6 Required no. of categories
in IV.
7 Required assumptions to
apply this statistical test.
8 State a practical example
for applying the Wilcoxon
Sign Rank test with null
and alternative hypotheses
(16 Marks)

(Total 25 Marks)

6
Question No.05
Suppose that you are working in “Alpha Fashion Company” (large readymade garment factory)
as a researcher. The company has identified that occupational dissatisfaction would be an
unpleasant condition that highly affects organizational performance. Thus, you have been assigned
to study employees’ occupational stress.

You are interested in examining whether employees' levels of occupational stress differ based on
their different age categories. Suppose that for the study, you have drawn a sample from the
Fashions company by using a stratified random sampling technique and categorized three age
groups as Generation (z), generation (y), and generation (x).

You are required to answer the following questions.

(a) To achieve the research objective of the company a statistician has advised you to apply
One-way ANOVA. Hence justify reasons behind this selection stating key assumptions
under that selection.
(04 Marks)
(b) Write down suitable research questions and hypotheses (null and alternative) for the
scenario mentioned above.
(04 Marks)
(c) Suppose the following outputs are obtained after performing One Way ANOVA through
the SPSS.

Occupational Stress: Descriptive Statistics

95% Confidence Interval for

Std. Std. Mean

Item N Mean Deviation Error Lower Bound Upper Bound Minimum Maximum
Generation Z 28 2.1739 .92183 .17421 1.8165 2.5314 1.00 5.11
Generation Y 21 3.0517 .71532 .15610 2.7261 3.3774 2.00 5.00
Generation X 51 3.3478 1.03764 .14530 3.0559 3.6396 1.22 5.00
Total 100 2.9569 1.06438 .10644 2.7457 3.1681 1.00 5.11

7
 Test of Homogeneity of Variances

Occupational Stress

Levene Statistic df1 df2 Sig.

2.776 2 97 .067

ANOVA
Occupational Stress
Sum of Squares df Mean Square F Sig.
Between Groups 25.146 2 12.573 14.016 .000
Within Groups 87.012 97 .897
Total 112.158 99

Multiple Comparisons
Dependent Variable: occupational stress
Tukey HSD
(J) Age Mean Difference Std. 95% Confidence Interval
(I) Age Categories Categories (I-J) Error Sig. Lower Bound Upper Bound
Generation Z Generation Y -.87782* .27341 .005 -1.5286 -.2270
Generation X -1.17385* .22277 .000 -1.7041 -.6436
Generation Y Generation Z .87782* .27341 .005 .2270 1.5286
Generation X -.29603 .24557 .453 -.8805 .2885
Generation X Generation Z 1.17385* .22277 .000 .6436 1.7041
Generation Y .29603 .24557 .453 -.2885 .8805
*. The mean difference is significant at the 0.05 level.

Using the above SPSS outputs which are relating to the One-Way ANOVA, you are
required to provide answers for the following.
(i) Interpret each of the above SPSS output and Test the hypotheses that you stated in
part (b).
(ii) Based on the given output results, report your conclusions.
(10 Marks)

8
(d) The training and development program was organized by the top management of
Gamma LTD to improve the performance of their workers and the company has spent a
considerable amount of money on this program. The company has measured its
performance before the training and development program and six months after the training
and development program.

The statistician of the company decided to run paired sample – t-test to measure the success
of the program and you are given SPSS outputs as follows.

Using the above SPSS outputs, you are required to,

(i) construct hypotheses to test whether the training and development program success
or not in terms of employee performance.
(ii) Test your hypotheses using the above SPSS outputs and report your conclusion.
(07 Marks)
(Total 25 Marks)