The chapter focuses
on the research method that will be adopted. Regression analysis based on the
classical linear regression model, otherwise know as ordinary least square
(OLS) technique is chosen by the researcher. The researcher’s choice of
technique is based not only by its computational simplicity but also as a
result of its optimal properties such as linearity, unbiasedness, minimum
variance, zero mean value of the random terms etc.(Koutsoyiannis, 2001, Gujarati
2004, Baltagi, 1999, and Nwobi, 2001).
MODEL SPECIFICATION
The
hypothesis of this study has been maintained on the assumption that Gross
Domestic Product (GDP) is determined by export promotion, imports and Exchange
rate. Hence, the model based on these variables in functional form.
GDP =
f(EXP, IMP, EXD)
------------------------ 3.1
Where
GDP
= Gross
Domestic Product
EXP = Export parameters
IMP = Import parameters
EXD = Exchange
rate parameters
The GDP is
the dependent variable while X, M, S, are all independent or explanatory
variables.
This can have
its linear function as:
GDP = β0 + β1
EXP +
β2IMP + β3EXD +
ut ----------------------- 3.2
Where
β0 = Constant
or intercept
β1 = Export
parameters
β2 = Import
parameters
β3 = Exchange
rate parameter
ut = Error
term
MODEL EVALUATION
Having
concluded with the estimation of the model, the next stage in any econometric
research work is the evaluation of the model, which consist of deciding whether
the estimation of the parameters are theoretically meaningful and statistically
satisfactory (Koutsoyiannis, 2001:25).
The
estimated parameters will be evaluated by determining whether they have
satisfied the statistical a priori criteria and econometric criteria.
i. Economic a priori criteria
Economic
a priori criteria are restrictions
imposed by theory concerning the sign and magnitude of economic parameter
estimate be the elasticity, the marginal values, properties, multipliers, etc.
economic theories defines the sign of the co- efficient and in broad lines
their magnitude (Koutsoyannis, 2001:25).
Assuming
estimates of the parameters turn up with signs or size not in conformity with
economic theory, they should be rejected, unless there is a good reason to
believe that in the particular instance the principles of econometrics theory
do not hold.
Consequently,
in the research work, it is expected that export promotion has a significant
impact in the growth of Nigeria economy. And should possibly be related to
import-export and exchange rate index of growth should be positive to the Gross
Domestic Product (GDP).
ii. Statistical Criteria:
The
statistical criteria otherwise known as the first order-test begins with the
coefficient of determination (R2) test. This is a test of goodness
of fit of the explanatory power of the regression model. It has a value if 0 and 1 is usually expressed as percentage.
It shows the variability of the dependent variable caused by changes in the
explanatory variables.
The next
to be conducted is the student t- test. This is a teat of significant of
individual parameters estimates. It will be tested using 5% level of
significance. This test will be followed by the standard Error test, it is used
to test for the statistical reliability of the coefficient estimate.
Decision
Rule:
If t-calculated value is greater than
the t-tabulated value, reject the null hypothesis otherwise accept it.
If S(b1) < b1/2,
reject the null hypothesis other accept and conclude that coefficient estimate
of b1 is not statistically reliable.
If F-calculated value is greater than
the F-tabulated value, reject the null hypothesis and conclude that the entire
regression plane is statistically significant.
iii. Second Order (Durbin Watson Test)
The Durbin Watson test is a test of
serial or autocorrelation in the mode. This test will also be conducted at 5%
level of significance.
Decision
Rule:
If the computed Durbin Watson
statistics is less than the tabulated value of the lower limit, there is
evidence of positive first order serial correlation. If it is greater than the
upper limit there is no evidence of positive first order serial correlation.
However, if it lies between the lower and upper limit, there is inconclusive
evidence regarding the presence or absence of positive first order serial
correlation. The implication is to know if important variables are captured in
the model.
SOURCE OF DATA
The data for this research project is
obtained from the following sources:
i.
Central bank of Nigeria statistical bulletin
for various years.
ii.
Central Bank of Nigeria Annual Account for
various years.
iii.
Other CBN periodicals – Bullions of various
years.
THIS PROJECT WORK WAS WRITTEN BY
AND SUBMITTED TO THE DEPARTMENT OF ECONOMICS
OCTOBER 2010