Gross regional domestic product estimation: Application of two-way unbalanced panel data models to economic growth in East Nusa Tenggara province

The condition of East Nusa Tenggara Province which recently developed new districts can affect the number of information or data collected become unbalanced. One of the consequences of ignoring the data incompleteness is the estimator become not valid. Therefore, the analysis of unbalanced panel data is very crucial.The aim of this paper is to find the estimation of Gross Regional Domestic Product in East Nusa Tenggara Province using unbalanced panel data regression model for two-way error component which assume random effect model (REM). In this research, we employ Feasible Generalized Least Squares (FGLS) as regression coefficients estimation method. Since variance of the model is unknown, ANOVA method is considered to obtain the variance components in order to construct the variance-covariance matrix. The data used in this research is secondary data taken from Central Bureau of Statistics of East Nusa Tenggara Province in 21 districts period 2004-2013. The predictors are the number of labor over 15 years old (X₁), electrification ratios (X₂), and local revenues (X₃) while Gross Regional Domestic Product based on constant price 2000 is the response (Y). The FGLS estimation result shows that the value of R² is 80,539% and all the predictors chosen are significantly affect (α = 5%) the Gross Regional Domestic Product in all district of East Nusa Tenggara Province. Those variables are the number of labor over 15 years old (X₁), electrification ratios (X₂), and local revenues (X₃) with 0,22986, 0,090476, and 0,14749 of elasticities, respectively.