Get Complete Project Material File(s) Now! »

**CHAPTER THREE ****RESEARCH METHODOLOGY**

This chapter is concern with the presentation of research methodology employed in the study that is the acquisition of relevant data and analyzing the same, using appropriate statistical tools.

Modem modeling strategies are data centered as they allow data play strategic roles in the analysis of observation. This is in content with the view of the traditional modeling practices, which sees specification of model as an exclusive domain of theory. Modem modeling approach however, includes the specification searches guided by theory as an integral part of data analysis. Data are therefore allowed to play an active role in determining among rival specifications the best.

In this research work, the Explanatory Data Analysis (EDA) which is one of the modem modeling approaches will be employed. The EDA emphasizes mainly on learning *from* data as to arrive at an explanation. The reason being that data by themselves are useless without an interpretation.

**Model Specification**

Now, it is obvious that non-oil export is not the only independent variable that Gross Domestic Product (GDP) in Nigeria. As such, other variables do affect GDP.

Specification of model involves the variables which will be included in the model; the appropriate expectations about the sign and size of the parameter of the function, and (he mathematical forms of the model. There are several economic models that can be used to dive the estimators of the parameters of economic relationships. In this study, a two-way multiple regression model is used to analysis and establish the relationship variable. The two-way multiple regression techniques is used because I gives he best fit, and is an unbiased estimator. 3.2 Definition of Variable In the Nigerian economy, economy growth (GDP) is associated with Various micro-economic variables. Among these variables included are:

GDP: Gross Domestic Product at current market prices.

Non-oil: Non-oil exports revenue.

**Oil: **Oil Export Revenue

GEX:Government expenditure

The functional form of this model is as thus: GDP = f (NON-OIL, OIL, GEX) the learner functional forms are as thus

GDP = b_{0} + b_{1} NON-OIL, + b_{2} OIL+ **b**_{3}*GEX + U* Where t= 1984-2003

**B**** _{o}** = Intercept Term

B

_{1-3}= Regression Co-efficient

U = The error or disturbance term.

** Assumptions of the Error Term (U)**

According to Kousoyiannis (2003), the following are the assumptions of the error term (U):

- U is a random real variable
- The mean of U is zero at any particular time.
- Homoscedasicity or constant variable of U.
- The variable U has a normal distribution
- The explanatory variables are measure without error.
- U is independent of the explanatory variables
- Non-autocorrelation of U.
- The model is correctly specified.
- The model is correctly identified.
- The macroeconomic variables are correctly specified. Based on these assumptions, we build our model.

**Nature and Scope of Data Collection**

The study makes use of secondary data sourced from institutions like the Central Bank of Nigeria (Annual reports and statistical bulletin). Others include Caritas University Library, Federal Office of Statistics (FOS). The study covers the period, from 1986- 2000

**Method of Data Analysis**

The study makes use of ordinary least square (OLS) method of data analysis. We adopt the ordinary least square criterion because the alternative criteria or econometric techniques like the two-stage least square (2 SLS), full information maximum likelihood (FLML) among others, are more sensitive to specification errors of autocorrelation and regression than the OLS. The ordinary least square (OLS) estimator possesses the Blue (Best linear Unbiased Estimate) properties, which include, efficiency, consistency and unbiasness. The P.C. give 8.0 Computer software was applied for the analysis of data.

**Testing of Hypotheses**

The above hypotheses will be tested at 5 percent or 0.05 level of significance. The null hypothesis is acceptable if the probability at which the t-value is significant is greater than the chosen level of significance. Otherwise, the alternative hypothesis will be accepted, for the entire variable included.

**Evaluation of Model**

**Evaluation based on Economic Apriori Criteria**

This test is carried out to check if the signs and magnitudes of the estimated parameters conform to what economic theory postulates.

**Evaluation based on statistical criteria**

The coefficient of determination (R^{2})

Thus R^{2} explains the total variation in the dependent variable (GDP) caused by variations in the explanatory variable included in the model.

**The F- Test**

This test is used to test whether the variables included on the work are significant or not in determining the level of domestic saving in Nigeria. Each element of s follows the distribution with N-K degree of freedom.

Title page

Approval page

Dedication

Acknowledgment

Table of contents

Abstract

CHAPTER ONE: INTRODUCTION

1.1 Background of the study

1.2 Statement of problem

1.3 Objectives of the study

1.4 Significance of the study

1.5 Scope and Limitations of the study

CHAPTER TWO: LITERATURE REVIEW

2.1 Theoretical literature

2.2 Empirical literature

CHAPTER THREE: RESEARCH METHODOLOGY

3.1 Model Specification

3.2 Definition of variable

3.3 Assumptions of the error team (U)

3.4 Nature and scope of Data collection

3.5 Method of Data analysis

3.6 Testing of hypotheses

3.7 Evaluation of model

3.8 Sources of data and collection

CHAPTER FOUR: DATA PRESENTATION AND ANALYSIS OF RESULT

4.1 Presentation of Result

4.2 Evaluation of result

4.3 Hypothesis testing

CHAPTER FIVE: SUMMARY, RECOMMENDATIONS AND CONCLUSION

5.1 Summary

5.2 Recommendations

5.3 Conclusion

References

GET THE COMPLETE PROJECT

THE IMPACT OF NON-OIL EXPORT ON ECONOMIC GROWTH IN NIGERIA (1986-2010)