METHODOLOGY OF BUDGET DEFICIT (TECHNIQUES, MODEL, STATISTICAL TEST, DATA, E-VIEW)



ANALYTICAL FRAMEWORK
            The basic aim of any economic research is to combine economic theory and statistical techniques for inference to arrive at a given theoretical proposition. The economic theory states the nature of the hypothesis and through inference and different methods of estimation, the research tests to validate these hypotheses.
            Economic theory proposes in favour, neutrality and against budget deficit in an economy. These propositions were made by different economists. Some empirical works also favoured the above three distinct propositions while relating them with other macroeconomic variables. In order to study the Nigerian economy in the face of budget deficit, this study will employ econometric method as the research technique. This choice resulted from the need to study budget deficits, its relationship with
macroeconomic variables and the pace of economic growth in Nigeria.

MODEL SPECIFICATION
            An economic model is a representation of the basic feature of an economic phenomenon. It is also an abstraction of the real world. Model specification is based on the relevant information available for our study. Also, it depends on the theoretical and empirical works already studied.
            Two models will be used in this research work. The first is a linear model to capture the nature of the relationship between budget deficit and economic growth in Nigeria. The model will also be used to determine the macroeconomic variable that greatly influences budget deficit and Nigerian economic growth. The second model shows (represents) the model to be used for causality analysis between budget deficit and economic growth in Nigeria.
            The functional form of this models can be specified as follows:
BD       =          f(RGDP, CAD,RER,FGCE,RIR)    ………………………      3.1
Where:
            BD                   =          Budget deficit
            RGDP =          Real Gross Domestic Product
            CAD                =          Current Account Deficit
            REXR  =          Real Exchange Rate
            RIR                  =          Real Interest Rate
            Ut                    =          Stochastic Error Term
The BD is the dependent variable while RGDP, CAD, REXR, RIR are all independent or explanatory variables.
This can have its linear function as:
BD  =   β0  +   β1 RGDP  +  β2CAD +  β3REXR  +  β4RIR + Ut ----------     3.2
Where
β0        =          Constant or intercept
β1        =          Gross Domestic Product parameters
β2        =          Current Account Deficit parameters
β3        =          Real Exchange Rate parameter
β4           =          Real Interest Rate parameter
ut         =          Stochastic Error term

JUSTIFICATION OF THE MODEL
            The preference of these techniques in estimating the model is based on the fact that this work seeks to investigate the nature of the relationship between budget deficits and economic growth in Nigeria.
            The model also seeks to analyze the effect of macroeconomic variables on budget deficits. Thus, the ordinary Least Square (OLS) technique is most suitable for the estimation of this model.
            This work lays emphasis on the statistical significance of the variables. Thus, the Ordinary Least Square Estimation possesses the properties of Best Linear and Unbiased Estimator (BLUE) and also minimum variance and mean squared error estimator (Koutosyiannis, 1977). This technique is relatively simple to use in the analysis of this study.

ESTIMATION TECHNIQUES
            The major tasks in regression analysis are to estimate the population regression function on the basis of simple regression function as accurately as possible. This research has adopted the econometric method of Ordinary Least Square (OLS).
            Ordinary Least Square (OLS) is the researcher’s choice of estimation. The statistical test of parameter estimates will be conducted using their standard error, t-test, f-test, R2 (Coefficient of determination) and Durbin Watson (DW) test in order to enhance the robustness of the result.

TECHNIQUES FOR EVALUATION OF RESULTS
            According to Koutsoyiannis (1997), there as three criteria, which are used in the process of evaluation with the aim of ascertaining the estimates of the parameters are meaningful and statically significant. These criteria, which are stated below, will be used in the evaluation of the estimate obtained in this research work.

Economic Test (A Priori Expectation)
            Under this criterion, the a priori expectation (signs and sizes) of the parameter estimates of the variables in the model will be evaluated to check whether they conform to economic theory. The theoretical (a priori) expected sins of the macroeconomic variables used in the model are stated below:
β1 is expected to have a positive sign because as government spends more than its revenue, the economy tends to grow fast.
β2 is expected to have a positive sign because theoretically, budget deficit and current account deficit are positively related.
β3 is expected to have either positive or negative sign in accordance with Keynesian postulation in economic theory, that real exchange rate has a bidirectional relationship with economic growth.
β4 is expected to have a negative sign because as budget deficit increases interest rate decreases.

STATISTICAL (FIRST ORDER) TEST
The coefficient of Determination (R2)
            The R2 explains the total variation of the dependent variables caused by variables in the explanatory variables included in the model.
Student T- Test
            The test is used to check whether the variables included in this study are significant or not in determining the level of macroeconomic variables impact on budget deficit. Each element (parameters) follows the t-distribution with n-k degree of freedom.
F-test
            The test will be adopted to test the overall significance of the regression model
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.

SOURCE OF DATA
            The date for this study is secondary data sourced from Central Bank of Nigeria Statistical Bulleting and National Bureau of Statistics.

SOFTWARE PACKAGE
Share on Google Plus

Declaimer - Unknown

The publications and/or documents on this website are provided for general information purposes only. Your use of any of these sample documents is subjected to your own decision NB: Join our Social Media Network on Google Plus | Facebook | Twitter | Linkedin

READ RECENT UPDATES HERE