<![CDATA[Hourly wage disparities in Indonesia reflect complex regional economic conditions that vary across provinces. These disparities are closely related to spatial factors, as economic conditions in one region may influence neighboring regions. This study aims to compare the performance of the Ordinary Least Squares (OLS) linear regression model and the Spatial Durbin Model (SDM) in identifying the determinants of hourly wages in Indonesia. The study uses secondary data from BPS Indonesia for 2023, covering 34 provinces. Predictor variables used including the poverty gap index, expected years of schooling, GRDP per capita, and the percentage of poor population. Spatial effects were examined using Moran’s I and the Breusch-Pagan test. The test results indicate the presence of both spatial dependence and heterogeneity in provincial hourly wages, suggesting that the OLS model is insufficient to capture spatial interactions between regions. Therefore, the Spatial Durbin Model is applied to accommodate both direct effects and spatial spillover effects. The empirical results of the SDM show that the poverty gap index and GRDP per capita have significant direct effects on hourly wages at the provincial level. In addition, the poverty gap index and expected years of schooling exhibit significant indirect effects. Model performance was evaluated using the coefficient of determination (R-Square), Mean Square Error (MSE), Mean Absolute Error (MAE), and Mean Absolute Percentage Error (MAPE). The results show that the Spatial Durbin Model outperforms the OLS model, as indicated by a higher R-Square value and lower MSE, MAE, and MAPE values. ]]>
Copyrights © 2026
