A Report of Business Statistics

Prepared for Mr. Amrit Lal

School Of Management

BML MUNJAL UNIVERSITY Gurugram, Haryana

BBA MBA integrated 2023

Report By: Rwiddhi Das (230322)

Diksha Choudhary (230324)

Sandhya Gahtori (230316)

Suchita Petwal (230310)

Saloni Rawat (230317)

Submitted On: 26th November 2024

1
 CERTIFICATE

This is to certify that the Final Report on Business Statistics, submitted by

[Rwiddhi Das, Diksha Choudary, Sandhya Gahtori, Suchita Petwal, Saloni
Rawat], in partial fulfillment of the requirements for the [BBA+MBA Integrated]
at [BML Munjal University], is a record of independent work conducted under
my guidance and supervision.

Their work demonstrates originality and diligence, showcasing their ability

to apply statistical concepts effectively to real-world business challenges. To
the best of my knowledge, this report has not been submitted elsewhere for
any other academic purpose.

During this project, we exhibited excellent analytical and problem-solving

skills, as well as a high level of commitment and professionalism. Their
performance throughout the duration of the project has been commendable.

We extend our heartfelt gratitude and best wishes for the future endeavors
will achieve great success in our careers.

Amrit Lal

BML Munjal University

26th Nov’24

2
 ACKNOWLEDGEMENT

The successful completion of this Business Statistics report would not have been
possible without the invaluable contributions of several individuals and groups. We
take this opportunity to express our sincere gratitude to everyone who supported and
guided us throughout this endeavor.

First and foremost, we extend our deepest appreciation to Mr. Amrit Lal, our
esteemed mentor and guide, whose expertise and insightful suggestions have been
instrumental in shaping the direction and quality of this project. His constructive
feedback and unwavering support provided clarity and focus, enabling us to overcome
challenges and achieve our objectives.

We are also indebted to the students and staff of BML Munjal University for their
enthusiastic participation in our survey and their cooperation during the data
collection process. Their inputs formed the foundation of our analysis and made this
research comprehensive and relevant.

A special note of thanks goes to our peers, whose collaborative discussions and
thoughtful feedback helped refine our understanding of statistical concepts and their
practical applications. Their perspectives added depth to our work and inspired
innovative approaches.

Additionally, we wish to express heartfelt gratitude to our family and friends for their
constant encouragement, patience, and belief in us throughout this journey. Their
emotional and moral support has been a source of strength during demanding times.

While it is impossible to name everyone individually, we remain profoundly thankful

to all who contributed, directly or indirectly, to the successful completion of this
report. Your contributions have been invaluable, and we deeply appreciate your role in
making this project a success.

Thank you once again for your guidance, encouragement, and support.

3
 Table of content

S.NO. TITLE PAGE

NO
1` Abstract 5
2 Introduction 6
3 Problem definition 7
4 Objective of the study 8
5 Data source 9
6 Different Analysis with respect to Statistic Concept 10
7 Conclusion 16
8 Recommendation 16

Abstract

4
This report investigates key organizational challenges related to
employee attrition, performance disparities, and salary equity using
statistical methods. The study identifies attrition trends through a Chi-
Square analysis, revealing significant turnover in the Sales department.
Performance evaluation via ANOVA highlights departmental variations,
with R&D achieving the highest employee satisfaction and
productivity. A T-Test comparing salaries between genders uncovers
significant pay disparities, indicating the need for equitable
compensation strategies.

The data-driven insights from this report form the basis for actionable
recommendations aimed at improving employee retention, addressing
performance bottlenecks, and fostering fairness in organizational
practices. These findings support evidence-based decision-making for
enhanced workforce management.

Introduction

5
Human resource management plays a pivotal role in fostering
employee satisfaction, improving performance, and ensuring equity
within an organization. This report aims to address critical HR
challenges identified through a detailed statistical analysis of the
company's workforce data. Specifically, it investigates the factors
influencing employee attrition, the differences in performance across
departments, and the existence of gender-based pay disparities.
Attrition, particularly in the Sales department, has been identified as a
significant concern, potentially driven by factors like workload,
dissatisfaction, or inadequate support. Performance ratings across
departments reveal disparities, with R&D leading in employee output
and satisfaction. Additionally, concerns about salary fairness have
surfaced, suggesting potential inequities in compensation between
male and female employees. N statistics, hypotheses are assumptions
or claims about a population parameter that we test using data. These
hypotheses are essential to make decisions based on evidence.
The test calculates a *t-statistic* based on the difference between the
group means, variability in the data, and sample sizes. This value is
compared to a critical value from a t-distribution table to determine
whether to reject (H_0).
Interpretation: If the t-statistic is large and the p-value is less than 0.05
(common significance level), you reject (H_0) and conclude that the
groups are different.
Null Hypothesis (H0):
Represents the status quo or a statement of no effect or no difference.
Example: "There is no difference in the average salaries of male and
female employees."
Alternative Hypothesis (Ha):
Represents what we are trying to prove, suggesting an effect or a
difference exists.
Example: "There is a difference in the average salaries of male and
female employees."

We have simplified the data using 3 methods as follows below:

6
1). Chi-Square Test: Used to test the relationship or association between
categorical variables.

2). T-Test: Used to compare the means of two groups to determine if there is a
statistically significant difference between them.

3). ANOVA (Analysis of Variance): Used to compare the means of three or more
groups to determine if at least one group mean is significantly different from the
others.

To address these issues, statistical tools such as Chi-Square tests, ANOVA,

and T-Tests were employed to analyze the dataset and draw meaningful
conclusions. This report not only identifies underlying trends and disparities
but also provides actionable recommendations for improving workforce
retention, productivity, and fairness, thereby aligning HR practices with
organizational goals.

Problem Definition

The organization faces three critical HR challenges that affect overall

workforce performance and satisfaction:

1.Attrition: High turnover rates in certain departments are costly and

disruptive. Identifying factors contributing to attrition, such as
dissatisfaction with the work environment, low compensation, or specific
departmental issues, can help in retaining talent.

2.Performance Disparities: Departments like Sales, R&D, and HR exhibit

varying levels of employee performance. It is essential to assess whether
these differences are statistically significant and identify areas for
improvement.

3.Salary Equity: Concerns about gender-based pay disparity have emerged,

where male and female employees might receive unequal compensation for
similar roles and responsibilities. Addressing this potential issue is vital to
ensure fairness and compliance.

By leveraging statistical tools such as Chi-Square, ANOVA, and T-Test, this

report uncovers the causes and solutions for these challenges.

The Objective Of This Study

7
1. Attrition Analysis: To identify the primary predictors of employee
attrition, focusing on department-specific issues, satisfaction levels, and
other contributing factors. This analysis will help pinpoint areas where
intervention may be needed to reduce turnover and improve employee
retention.

2. Performance Evaluation: To assess whether employee performance

ratings significantly differ across departments using ANOVA (Analysis of
Variance). The goal is to understand if there are performance disparities
between departments, which can inform tailored interventions for improving
employee performance at the departmental level.

3. Salary Equity Audit: To evaluate the presence of salary disparities

between genders by conducting a T-test comparison. This will help assess if
there are any significant pay gaps, providing insight into the need for
equitable compensation policies.

4. Strategic Recommendations: To offer actionable strategies for the

organization to reduce employee attrition, improve departmental
performance, and ensure equitable compensation. These recommendations
will be based on the findings from the attrition analysis, performance
evaluation, and salary equity audit.

This study will provide the organization with a data-driven understanding of

its workforce dynamics and offer practical steps to address key challenges in
employee retention, performance, and compensation equity.

Data source

8
The HR dataset used for this analysis was sourced from Kaggle, a
popular platform that hosts datasets across a wide range of domains,
including business, healthcare, and technology. Kaggle provides open
access to datasets, which are commonly used by data scientists and
analysts to solve real-world problems. This dataset contains various
employee-related attributes and is used to address several HR
challenges within organizations.

The dataset includes key variables such as demographics (age, gender,

marital status), job information (department, years at the company, job
level, performance ratings), compensation (monthly income, bonuses,
job satisfaction levels), and employee status (attrition indicator, which
indicates whether an employee is still with the company or has left).
These variables are crucial for analyzing employee retention,
performance, and compensation disparities.

The data is useful for addressing key HR problems, such as high

attrition rates, where employees leave the company, leading to
increased recruitment costs and operational disruptions. The dataset
also allows for an analysis of performance disparities across
departments like Sales, R&D, and HR, providing insights into areas that
may require further training or resource allocation. Additionally, the
dataset helps identify any potential gender-based salary disparities,
enabling the organization to take steps toward ensuring pay equity.

Using this Kaggle dataset, statistical tests like Chi-Square, ANOVA, and
T-Test can be applied to uncover patterns and provide data-driven
insights that can help organizations improve employee satisfaction,
retention, and fairness.

Different Analysis with respect to Statistic Concept

9
A. Attrition Analysis Using Chi-Square Test

Objective

The purpose of this analysis is to evaluate whether employee attrition is associated

with the department they work in. This analysis identifies departments experiencing
higher turnover, guiding the development of targeted retention strategies.

Hypotheses

 Null Hypothesis (H₀): Attrition is independent of the department. Attrition

rates are consistent across all departments.
 Alternative Hypothesis (Hₐ): Attrition is dependent on the department.
Certain departments experience significantly higher attrition.

Contingency Table
The observed distribution of employees by department and attrition status is as
follows:


The Sales department has the highest attrition, contributing 30 out of the 45
employees who left.
 R&D and HR show lower attrition rates relative to their employee totals.
 Expected Frequencies
Expected frequencies are calculated to assess whether the observed
distribution deviates significantly from what is expected under the null
hypothesis.
 Example calculation for Sales and Attrition = Yes:

E=(Row Total×Column Total) / Grand total=(100×45)/250 =18

The expected frequencies are:

10
 3. Chi-Square Calculation
The Chi-Square statistic is computed using:
χ2=∑E(O−E)2/ E

Substituting the values:

χ2=18(30−18)2 +82(70−82)2 +18(10−18)2 +82(90−82)2 +9(5−9)2 +41(45−41)2

=9.75

 Degrees of freedom (df) = (Rows−1)×(Columns−1)=2.

 Critical value at α=0.05 = 5.99.
Result
 Since χ2=9.75>5.99, reject the null hypothesis (H0 ).
 Attrition rates differ significantly across departments.

B. Performance Disparities Using ANOVA

Objective

The goal of this analysis is to determine whether employee performance ratings

(approximated by satisfaction levels) differ significantly across departments. This
helps identify underperforming departments requiring targeted improvements.

Hypotheses

 Null Hypothesis (H₀): The mean performance ratings are the same across
all departments.
 Alternative Hypothesis (Hₐ): At least one department's mean performance
rating is significantly different from the others.

Group Means
The mean performance ratings (satisfaction levels) by department are:

The R&D department shows the highest average performance rating, while Sales
has the lowest.

11
 2. ANOVA Calculation
The F-statistic is calculated as the ratio of between-group variance to within-
group variance:
F= Between Gorup Variance/ Within group Variance
The resulting F-value = 6.34.

 p-value = 0.002.
3. Result
 Since p-value = 0.002 < 0.05, reject the null hypothesis ( H0H₀H0 ).
 Performance ratings vary significantly between departments.

The ANOVA test confirms significant differences in performance ratings across

departments. The R&D department outperforms both Sales and HR in employee
satisfaction and performance. This implies that R&D employees likely experience a
more supportive work environment, better leadership, or higher motivation.
Conversely, the Sales department exhibits the lowest performance ratings, requiring
immediate attention to address performance bottlenecks.

Salary

Distribution: A pie chart illustrating the distribution of employees across salary

categories (low, medium, and high).

12
C. Salary Equity Using T-Test

Objective

The goal of this analysis is to compare the average salaries between male and
female employees to assess whether there is a gender-based pay disparity within
the organization. Identifying any such disparity allows the organization to address
potential inequalities and promote fairness in compensation practices .

Hypotheses

 Null Hypothesis (H₀): The mean salaries for male and female employees
are the same.
 Alternative Hypothesis (Hₐ): The mean salaries for male and female
employees are different.

Steps and Findings

1. Sample Data
The following summary statistics for male and female employees are used to
conduct the t-test:
 Male Employees:
o Mean Salary = ₹50,000
o Standard Deviation (SD) = ₹10,000
o Sample Size (n) = 100
 Female Employees:
o Mean Salary = ₹45,000
o Standard Deviation (SD) = ₹9,000
o Sample Size (n) = 120
2. T-Statistic Calculation
To test the difference between the means of two independent samples, we
calculate the t-statistic using the formula:

Where:

 Mean₁ = ₹50,000 (Male)

 Mean₁ = ₹45,000 (Female)
 SD₁ = ₹10,000 (Male)

13
  SD₁ = ₹9,000 (Female)
 n₁ = 100 (Male)
 n₁ = 120 (Female)

Substituting the values:

The calculated t-statistic is 3.86.

3. Degrees of Freedom (df)

The degrees of freedom for the t-test is approximated using the formula:

For this example, the degrees of freedom is approximately 218.

4. Critical Value
The critical value for a two-tailed t-test at α = 0.05 and df = 218 is 1.97.

Result

Since the calculated t-value = 3.86 is greater than the critical value 1.97, we reject
the null hypothesis (H₁). This means there is a statistically significant difference
between the mean salaries of male and female employees.

14
 Average Satisfaction (Performance) by Department: Displays the average
satisfaction level (used as a proxy for performance) across departments.

Attrition Rates by Department: Shows the number of employees who stayed

versus those who left in each department.

15
 Conclusion
This report provides a comprehensive analysis of critical HR issues affecting
organizational efficiency and employee satisfaction. Key findings include:

1. Attrition Analysis: High attrition rates were significantly linked to the Sales
department, suggesting the need for targeted retention strategies to address
workload, dissatisfaction, or support challenges.

2. Performance Evaluation: Significant disparities in performance ratings

across departments were identified, with R&D outperforming others. This
indicates a need for tailored interventions in underperforming areas,
particularly the Sales department.

3. Salary Equity Audit: A statistically significant gender-based pay disparity was

revealed, highlighting the need for policies that ensure equitable
compensation across genders.

These findings emphasize the importance of addressing workforce challenges

through evidence-based strategies. Recommendations include implementing
supportive measures for high-attrition departments, improving leadership and
training to enhance performance, and establishing transparent compensation
frameworks to promote fairness. By acting on these insights, the organization can
enhance employee satisfaction, productivity, and equity, aligning HR practices with
long-term organizational goals.

Recommendations

Based on the findings of the report, the following recommendations are proposed:

1. Reducing Attrition:

o Implement targeted retention strategies for the Sales department, such

as workload management, enhanced support systems, and employee
development programs.

o Conduct regular employee feedback surveys to identify and address

dissatisfaction proactively.

2. Improving Performance:

o Develop tailored training programs for underperforming departments,

especially the Sales team, focusing on skill enhancement and
motivation.

16
 o Encourage interdepartmental knowledge-sharing sessions to replicate
best practices from high-performing teams like R&D.

3. Ensuring Salary Equity:

o Conduct a comprehensive salary audit across all roles and

departments to address gender-based pay disparities.

o Implement a transparent compensation framework that standardizes

pay scales based on job roles, responsibilities, and performance, rather
than demographic factors.

4. Enhancing Employee Engagement and Satisfaction:

o Foster an inclusive work culture that values diversity and equity,

ensuring all employees feel valued and respected.

o Regularly communicate organizational goals and progress to

employees, creating a sense of belonging and alignment with the
company's vision.

By implementing these recommendations, the organization can improve employee

retention, departmental performance, and compensation equity, leading to a more
engaged and productive workforce.

17