Building an Efficient Model by Using Panel Data

Abstract

The panel data models have gained great attention because they consider the effect of changing time series and the cross-sectional units. It has a higher number of degrees of freedom and is, therefore, more efficient.  Our research aims to build the most efficient model using panel data through comparison among six statistical models and to determine the most efficient model through the mean squares of error (RMSE) and the coefficient of determination (R2). Using the EViews-12 package to apply to two data sets to determine the most efficient model. The more critical findings are that the hypothesis assumed by the research states that the accuracy of the adopted models varies. Furthermore, it was found by building six types of panel data models that the best model is the (Two-way Fixed Effect Model) because it achieves the lowest value of (RMSE) and the largest value of R2.