B21100083

Bachelor of Bsuiness Administartion

Bachelor of Transportation and Logistics

FINAL EXAMINATION
COURSE: BBA1033 / UPS1014
COURSE CODE: Business Statistics / Probability and Statistics Release Date: 16 March 2022
Submission Date: 16 March 2022
Time: 9.00- 13.00

INSTRUCTIONS TO CANDIDATES:

1. This is an open book examination.

2. Open up the word document on your digital device. Write in all your answers as
required by each question.
3. Remember to SAVE your document. Submit to the link provided in the BLMS.
4. This question paper consists of ONE (1) parts.
5. Answer ALL questions.

Elizabeth A/P
B21100083 Arasilankumaran

STUDENT’S INDEX NO. : 0952

LECTURER : Professor Dr Shaheen Mansori

1
 B21100083

CONTENTS

S. No Contents Page Number

1 Introduction ( Question 1) 3

2 Hypotesis Testing 4

3 Conclusion 5

4 Introduction ( Question 2) 6

5 Multiple Regression analysis (a) 7

6 Multiple Regression analysis (b) 8

7 Multiple Regression analysis (c) 8

8
8 Multiple Regression analysis (d)

9
9 Multiple Regression analysis (e)

9
10 Multiple Regression analysis (f)

9
11 Multiple Regression analysis (g)

10
12 Conclusion

10
13 Refrences

2
 INTRODUCTION

A labour union is a group of workers who come together to bargain with

employers over salaries and working conditions. A labour union aims to shift
the power balance between employers and employees by requiring
businesses to engage with employees as a group rather than as individuals.
Collective bargaining is the term used to describe negotiations between
unions and businesses. Data on trade union membership, collective
bargaining coverage, and 1 strikes and lockouts provide governments and
social partners with information that allows them to better understand the
evolution of trends in industrial relations in order to adopt policies that
promote collective bargaining and sound industrial relations, as well as
evaluate those policies.

Question 1:
The Excel file Unions and Labor Law Data reports the percentage of public‐ and
private‐sector employees in unions in 2020 for each state, along with indicators
whether the states had a bargaining law that covered public employees or right‐to‐
work laws.
a. Develop and test the hypothesis that the percentage of employees in unions
for both the public sector and private sector is the same for states having
bargaining laws as for those who do not.
b. Test the hypothesis that the percentage of employees in unions for both the
public sector and private sector is the same for states having right‐to‐work
laws as for those who do not.

CONCLUSION
Only when employees possessed high talents, and there were few workers with those skills,
were unions successful in solving their problems. Unions, on the other hand, aided other
workers by drawing attention to their low pay and poor working conditions.

INTRODUCTION

Salary surveys are instruments for determining the pay levels for employees in one or more
jobs. Salary data from a variety of employers is reviewed in order to determine the amount
of pay paid. One or more job titles, job grades, geographic regions, employer size, and/or
sectors may be the topic of a survey. Survey vendors or HR consultants are typically hired
to perform salary surveys. Some employers do it themselves, but it is unreliable.

Data from surveys is frequently time-sensitive and can soon become out-of-date. Surveys
are frequently identified by the year or quarter in which the data was collected, due to the
time-sensitive nature of the information. Monthly or quarterly surveys perform best in high-
inflationary contexts, because many companies will alter their salary to keep up with
inflation.
 Questions 2:

The Excel file Salary Data provides information on current salary, beginning salary,
previous experience (in months) when hired, and total years of education for a
sample of 100 employees in a firm. Develop a multiple regression model for
predicting current salary as a function of the other variables. Hint: You are required
to include the full result as part of your report

a. Develop a multiple regression model for predicting current salary as a function of the other
variables. Hint: You are required to include the full result as part of your report.

Multiple Regression Analysis

The multiple regression analysis for predicting current salary is given below

=Current Salary = - 4139.24 + 1.73 * Beginning Salary – 10.907 * Previous

Eperience + 719.122 * Education
b. What is estimated salary for a person with the following background;

• Beginning Salary: $ 28500

• Previous Experience (months): 65months
• Education (years): 17 years

=Current Salary = - 4139.24 + 1.73 * 28500 – 10.907 * 65 + 719.122 * 17

= $ 56688.7642
Thus, the predicted current salary is $ 56688.7642

c. Interprate if the developed model is significant

Test Used: F test

F test statistic: 130.52
P – Value: p < 0.001
Conclusion: The regression model is good fit in predicting current salary

d. State the suitable hypostases Hypotheses.

Null Hypothesis: H0: β1 = 0

That is, the coefficient of Beginning Salary do not change from zero

Alternative Hypothesis: Ha: β2 ≠ 0

That is, the coefficient of Beginning Salary not equal to zero

The t test statistic: 15.203

P – Value: p < 0.001

Conclusion: Beginning salary significantly predicts current salary

Null Hypothesis: H0: β2 = 0

That is, the coefficient of previous experience do not change from zero

Alternative Hypothesis: Ha: β2 ≠ 0

That is, the coefficient of previous experience is different from zero

The t test statistic: - 1.404

P – Value: 0.164

Conclusion: previous experience is not a significant predictor current salary

Null Hypothesis: H0: β3 = 0

That is, the coefficient of education do not change from zero

Alternative Hypothesis: Ha: β3 ≠ 0

That is, the coefficient of education is different from zero

The t test statistic: 2.045

P – Value: 0.044 < 0.05

Conclusion: Education significantly predicts current salary

e. Interpret the R2

The coefficient of determination is 0.803 indicating that 80.3% of the dependent variable current salary
is predicted by the independent variables in the regression model. That is, 80% of the data fits the
regression model

f. Find the best model for predicting current salary using the p‐value criterion. Hint: You are required to
report the result for each stated hypothesis based on the results.

The p – value falls well below 0.05 indicating that the Beginning salary significantly predicts current
salary

The p – value 0.164 > 0.05 indicating that the previous experience is not a significant predictor current
salary

The p – value 0.044 < 0.05 indicating that the education significantly predicts current salary

Here, we see that Beginning Salary and Education significantly predicts current salary. Thus, we can
conclude that the best model to predict current salary is the model that uses Beginning Salary and
Education as independent variables

g. Based on these results, what would be your piece of advice for a job seeker?

The regression analysis clearly shows that Beginning Salary and Education significantly predicts
current salary while the p – value of previous experience falls above 0.05 (insignificant predictor of
current salary). Thus, a job seeker with high beginning salary and good education qualification has
higher chance of getting high current salary.
 CONCLUSION

SALARY IS NOT SOMETHING WE SHOULD IGNORE, despite the fact that many of us don't
want to spend too much time thinking about money or worrying about not making enough. The
widely recognised rule that it is not permissible to disclose pay information with coworkers has
solid justification—too much knowledge could foster an environment of jealousy or apparent
injustice—but not knowing how much one should earn causes plenty of confusion and
unfairness. Knowing roughly what the employee should make benefits both the business and
the employee.

REFERNCES

Lane, D., 2003. Introduction to Statistics. Rice University: David Lane

Tordeux A., 2017. Introduction to descriptive and parametric statistic with R,

Forschungszentrum Julich and Wuppertal University

Urdan, T., 2015. Statistics in plain english, third edition. [Place of publication not identified]:
Routledge.

Efron, B. and Hastie, T. (2021) Computer Age Statistical Inference, Student Edition:
Algorithms, Evidence, and Data Science. Cambridge: Cambridge University Press (Institute of
Mathematical Statistics Monographs). doi: 10.1017/9781108914062

END OF QUESTION PAPER