Employee engagement, productivity, and gross output were examined across different Mauritian industries. A simple linear regression found a strong relationship between employee engagement (measured by persons engaged) and productivity (measured by production units). A multiple linear regression found employee engagement was positively related to productivity but gross output was negatively related. Various statistical tests were conducted to ensure the model's validity. In conclusion, the study demonstrated employee engagement impacts productivity across industries while gross output decreases productivity.

1. THE IMPACT OF EMPLOYEE
ENGAGEMENT AND GROSS
OUTPUT ON PRODUCTIVITY IN
DIFFERENT INDUSTRY GROUPS

2. Outline of Presentation
 Introduction
 Literature Review
 Research Methodology
 Analysis
 Conclusion
Presented By
APPADU GANGAMAH DEVI
BAGHA KESHIKA
DIXIT CHANDREEKA
DOMUN NEERAJA
LUCKYRAM URVASHEE

3. CHAPTER ONE INTRODUCTION

4. INTRODUCTION
Industries in Mauritius
 Faced increased competition due to:
 Globalisation
 Changes in Technology
 Political and economic environment
 Must train employees to develop them to face competition
 Enhance the contribution as a means of sustaining effective performance and ensure output
 Training of employees can increase productivity and the output will be managed efficiently

5. INTRODUCTION
Overview of different industry in Mauritius
 Largest sector in Mauritian economy is Manufacturing industry , it contributed towards 20% to the GDP
 Construction industry make use of core values to contribute to economic growth
 Cohesiveness
 Integrity
 Developing people
 Building trust
 Responsibility
 Excellence
 Quality
 Financial and Insurance activities boost up the GDP contribution from Rs 31,263 millions in 2012 to Rs 32,799 Million in 2013
 Transport and Storage increased GDP from Rs 17,797 million in 2012 to Rs 18,784 million in 2013
 Mauritius remain the Information and Technology leader in the African region.

6. Problem Statement
 Productivity is affected due to
 Poor Supervision and management
 Poor communication
 Insufficient budgeting and staffing
 It has become a challenge to maintain a good workforce
 Moreover, preferences towards some employees might affect production thus resulting in
gender inequalities

7. Research Objectives
 To assess whether productivity, employee engagement and gross output are
related to each other
 To assess the link between productivity and employee engagement
 To measure the impact of gross output and productivity

8. CHAPTER TWO LITERATURE
REVIEW

9. Overview of this chapter
 Definition of employee engagement, productivity and output
 Constraints limiting output
 Productivity measurement
 Relationship between employment, output and productivity

10. Employee Engagement
 Extent to which employees feel passionate about their jobs
 Are committed to the organisation
 Put discretionary effort into their work
 Employ and express themselves physically, cognitively and emotionally during
role performances

11. Employee Engagement
 According to Gibbins work, there are 8 drivers of employee engagement which include:
 Trust and Integrity
 Nature of the job
 Line of sight between employees performance and company performance
 Career growth opportunities
 Pride about the company
 Co workers/ Team member
 Employee Development
 Relationship with one’s manager

12. Output
 Amount of goods and services produced in a system
 Constraints limiting output include:
 Quality of machinery
 Availability of workers
 Demand from consumers

13. Productivity
 Rate of efficiency by which a company produces goods and services

14. Productivity Measurement
 Technology
 Efficiency
 Real Cost savings
 Benchmarking Production Processes
 Living Standards

15. Relationship between Productivity, Employment
and Output
 Employment , productivity and output are not independently determined
variables that is , the 3 variables are linked
 It is expressed as Output = Employment * Productivity

16. CHAPTER THREE RESEARCH
METHODOLOGY

17. Research Methodology
 This chapter relates to the different methods used in this study and includes a
review of research design which consists of :
 Simple Linear Regression
 Multiple Linear Regression
 Hypothesis Development

18. Research Design
Simple Linear Regression
 The Dependent variable would be Production Units
 The Independent Variable would be Persons engaged
 The Equation is as follows:
 Y= B0+ B1X +
 Where Y would be the dependent variable, implying Production units
 X would be the independent variable, implying the Persons engaged
 Would be the Random error component

19. Multiple Linear Regression
 In this case, the Independent variables would be Persons engaged and Gross output
 The Dependent variable would be Production Units
 The Equation is as follows:
 Y= B0 + B1X1+B2X2+
 Where Y = dependent variable, implying Production Units
 X1= independent variable, implying Persons engaged
 X2= independent variable, implying Gross Output
 = Random error term

20. Sampling
 The sample size would be 12, comprising of
the different sectors namely:
 Manufacturing
 Construction
 Wholesale and retail trade
 Transportation and storage
 Accommodation and Food services
 Financial and Insurance activities
 Professional, scientific and technical activities
 Administrative and support service
 Education
 Human Health and social work
 Art and entertainment
 Other services

21. Research Tool
 The data would be mostly of secondary nature
 It was evaluated using the Integrated Statistical Software Stata 13.0

22. Research Questions
 What is the relationship between productivity, employee engagement and gross output?
 What is the link between productivity and employee engagement ?
 To measure the impact of gross output and productivity.

23. Hypothesis Development
 Hypothesis #1 : Productivity and Employee engagement
 H0: There is no relationship between productivity and employee engagement
 H1: There is a relationship between productivity and employee engagement
 Hypothesis #2: Gross Output , Productivity and Employee engagement
 H0: There is no relationship between gross output, productivity and employee engagement
 H1: There is a relationship between gross output, productivity and employee engagement

24. CHAPTER FOUR ANALYSIS

25. Contents
 Simple Linear Regression Model
 Multiple Linear Regression Model
 Post Estimation tests

26. Simple Linear Regression Model
 General equation: Y = B0 + B1X + Epsinote
 Where B0 is the Y-intercept and B1 is the gradient or slope
 Reg production person

27. Interpretation of Outcomes
 Equation of the Model: Production = 4.56+0.22 person engaged
 R2 is the proportion of variance in the dependent variable
 For this model, the value of R2 = 0.984

28. Hypothesis Testing
 Hypothesis #1
 H0: There is no relationship between productivity and employee engagement
 H1: There is a relationship between productivity and employee engagement
 Since the p -value of the model is 0.000 and less than the level of significance (0.05), the
null hypothesis is rejected. Hence, there is a relationship between person’s engagement
and production.

29. Multiple Linear Regression Model
 Reg production person output

30. Interpretation of Results
 General equation : Y = B0 + B1X+B2X+……BNX+ Epsinote
 Equation of this Model
 Production = 4.63 + 0.254 Person Engaged – 0.0000269 Gross Output

31. Hypothesis Testing
 Hypothesis #2
 H0: There is no relationship between gross output, productivity and employee engagement
 H1: There is a relationship between gross output, productivity and employee engagement
 Since the p -value of the model is 0.946 and greater than the level of significance (0.05), the
null hypothesis is accepted. Hence, there is no relationship between gross output and
productivity.

32. Comparative Analysis between Simple and
Multiple Regression Model
 Production = 4.56 + 0.255 person engaged
 Production = 4.63 + 0.254 person engaged – 0.0000269 Gross output

33. Post-Estimation Tests
 Statistical tests carried out for checking:
 Multicollinearity
 Homoskedasticity
 Heteroskedasticity
 Specification

34. Multicollinearity
 Multicollinearity refers when two variables are highly correlated, which may
create biased results.
 In order to detect for multicollinearity, the Variance Inflation Factors (VIF) test is
used.
 However, in case the VIF value > 10, there exists multicollinearity in the model.

35. VIF Test
 Upon using the VIF command, the VIF value was 1.01,which indicates that there is
no multicollinearity in this study.

36. Homoskedasticity
 One of the main assumptions for the ordinary least squares regression is the
homogeneity of variance of the residuals.
 Constant variance
 The command ‘robust’controls for Homoskedasticity in the regression model

37. Homoskedasticity
 reg production person output, robust

38. Heteroskedasticity
 The Breusch-Pagan test is used to check the linear form of Heteroskedasticity and it represents
the error variance.
 A larger Chi-square and a smaller p-value implies that there exists heteroskedasticity in the
model.

39. Link Test
 No other independent variables should be significant above chance in case a
regression equation is suitably specified.
 The hatsq is normally used as the p-value.
 If p-value < 0.05,Reject H0

40. Link Test Specification
 Link Test output

41. Conclusion
 In this research, we have shown employee’s engagement and output affect productivity of
the different industry groups in Mauritius.
 To have a clearer view of the impact, we had to make use of the simple regression and
multiple regression.
 The simple regression showed that the more people involve the more the production
would be. As concerned for multiple regression, productivity affects the gross output thus
decreasing it.

42. Thank You for your attention