Gross value added of agriculture sector in Bangladesh: an econometric investigation / Mehdi Rajeb, Mina Mahbub Hossain and Liton Chakraborty

In this paper we investigate how different factors, namely, land utilization, irrigated area, consumption of pesticide, area under forest, consumption of fertilizers and improved seeds affecting the Gross Value Added of agriculture sector in Bangladesh. The relationship between the concerned variables and their overall impact on the Gross Value Added of agriculture sector in Bangladesh have been examined through econometric modeling followed by various statistical measures like multivariate regression analysis, residual analysis, autocorrelation test, multicollinearity test and testing for the linearity of the regression. The results of this study suggest that all of the independent variables under consideration significantly influence the dependent variable. It is evident that the 89.60% variation in the dependent variable can be explained by the variation in the independent variables. All the properties of residual analysis (zero mean and constant variance) have been satisfied in this study and the results of both Run test and Durbin-Watson test show that residuals are uncorrelated. Finally, our regression model has been found to be approximately straight line whereas the results of Farrar-Glauber test indicate that multicollinearity exists in the model and all of the independent variables are found to be collinear. However, this could be removed with the help of Principal Component Analysis and other advanced techniques in further studies. The findings of this paper have important implications in identifying the factors which can accelerate growth in the agriculture sector of Bangladesh economy.