Dynamic Spatial Durbin Modeling (Case: Percentage of Poor Population in Indonesia 2010-2019)

Abstract

The dynamic panel model assumes that each observation unit is independent of each other. But sometimes this assumption is violated, so there are spatial effects in the model. This study aimed to make percentage modeling of poverty in Indonesia using the Dynamic Spatial Durbin Model (DSDM). The data used in this study were secondary data obtained from the Statistics Indonesia in the period 2010-2019. The parameter estimation method used in this model was the Maximum Likelihood (ML). According to Moral-Benito, Allison and Williams the ML method has the best performance when used on panel data that has small cross-section data dimensions. The results of this study indicated that spatial dependence, time lag, variables of Poverty Gap Index, Poverty Severity Index and Logarithm of Expenditures per Capita affect poverty in Indonesia significantly. Other results showed that DSDM was able to explain the diversity in models at 95.6 %. This seemed higher when it's compared to the Spatial Durbin Model (SDM). Thus, the result of the study proved that DSDM is the best model for modelling dynamic poverty data panel in Indonesia during 2010-2019.