ABSTRACT

This study investigated the relationship among blood pressure, age and body mass index.

The data used for this study were primary data collected from 191 randomly selected

participants comprising students and staff of Michael Okpara University of Agriculture,

Umudike. Scatter diagrams showing the relationship between blood pressure and each of

age and body mass index were ploted. It was observed that blood pressure and each of age

and body mass index are linearly related. A multiple linear regression model was then fitted

to the data. Residuals from the fitted mode! was found to be serially correlated. 'The general

least squares model was then fitted. The residuals from the generalized least squares satisfS'

the basic assumptions of multiple linear regression model. Hence, there is need for students

and academic staffs to be enlightened on the adverse health effects associated with high

blood pressure (BP) and high body mass index (BMI).

TABLE OF CONTENTS

Title page

Declaration

Certification

Dedication

Acknowledgement

Table of Content

List of Tables

List of Figures

Abstract

CHAPTER ONE: INTRODUCTION

1.1 Background of the Study 1

1.2 Statement of The Problem 1

1.3 Objective/Purpose of the Study 2

1.4 Scope of the Study 2

1.5 Definition of Term 2

1.6 literature Review 3

CHAPTER TWO: RESEARCH METHODOLOGY.

2. 1 Method of Data Collection 6

2.2 Method of data Analysis 6

2.3 Concept of Regression 6

2.4 Assumptions Underlying Multiple Linear Regression

2.5 Model Adequacy Checking/Residual Analysis

2.6 Normality test 8

2.7 Autocorrelation Test 10

2.8 Durbin-Watson test 11

2.9 Autocorrelation the Method of Generalized Least Square 12

2.10 Diagnostics check of Hetroscedasticity 13

2.11 Estimation of Parameters in Multiple Regression 13

2.12 Test for the Overall Significance in MLR 14

CHAPTER THREE: DATA ANALYSIS

3.1 Result and Discussions 17

3.2 Estimation of Parameters Using Matrix Format 18

3.3 Estimation of the Variances and Standard Errors 20

3.4 Test for Individual Significance of Regression Coefficient 21

3.5 Computing the Coefficient of Multiple Determination 23

3.6 Diagnostic Check; Detection of Model violation 23

3.7 Detection of Autocorrelation 24

3.8 Remedial Measure for Autocorrelation the Method of GLS 25

3.9 The White General Test for Hetroscedasticity 27

3.10 Test for Normality of the Residuals 28

CHAPTER FOUR:

4.1 Summary 30

4.2 Conclusion 30

4.3 Recommendation 31

References 32