Economic Inequality Analysis in Java: A MARS Model Approach

Diana Erviana (Department of Statistics, Universitas Islam Bandung.)
Teti Sofia Yanti (Department of Statistics, Universitas Islam Bandung)
Iwan Setiawan (Accounting Department, Politeknik Negeri Bandung.)

Indonesian Journal of Economics and Management
Vol. 6 No. 3 (2026): Indonesian Journal of economics and Management (July 2026)

Economic inequality in Java Island is a crucial issue that affects sustainable development. This study aims to model the Gini ratio using the Multivariate Adaptive Regression Splines (MARS) method. The secondary data used includes the response variable Gini ratio and predictor variables such as GRDP, Open Unemployment Rate, Percentage of Poor Population, Population Growth, and Labor Force Participation Rate. The best model was selected based on the replication with the lowest average Generalized Cross Validation (GCV) value. The analysis results indicate that the optimal model consists of 5 basis functions, derived from an initial selection of 15 basis functions, with a maximum interaction of 3 and a minimum observation of 3. This model has a GCV value of 0.001758381. The study findings show that the Labor Force Participation Rate and Population Growth Rate have equally high importance, indicating that these two variables are the key factors significantly influencing the model.