This research identifies regional variations and determinants of active family planning (KB) participation in East Java using spatial modeling. The study utilizes data from the 2024 Family Information System (SIGA) of BKKBN East Java. To address multicollinearity and high-dimensional data, the Elastic Net method—combining Ridge and Lasso penalties—was employed for variable selection, retaining 6 out of 10 initial variables. Global modeling through Ordinary Least Squares (OLS) showed an Adjusted of 0.668. However, a Moran’s I test on the residuals revealed significant spatial autocorrelation (Z-score = 2.5677, p = 0.0102), justifying the use of Geographically Weighted Regression (GWR). The GWR model, using a Fixed Gaussian kernel with a bandwidth of 103.63, improved performance with an Adjusted of 0.7348. The results demonstrate spatial heterogeneity, where factors such as unmet need, households with children, and welfare levels have varying impacts across different districts. This spatial visualization helps identify priority areas for strategic resource allocation to enhance KB program efficiency
Copyrights © 2026