GEOGRAPHICALLY WEIGHTED PANEL REGRESSION PADA PEMODELAN KASUS STUNTING DI NUSA TENGGARA TIMUR
DOI:
https://doi.org/10.24843/MTK.2026.v15.i04.p525Keywords:
Stunting, Panel Data Regression, Heterogeneity, GWPR, East Nusa TenggaraAbstract
Stunting is a chronic nutritional condition in children under five, characterized by height-for-age below the standard and associated with long-term impacts on human resource quality. The percentage of stunted toddlers in East Nusa Tenggara Province remains high, exhibiting spatial disparities and temporal fluctuations. This study aims to model and identify the factors influencing the percentage of stunted infants in East Nusa Tenggara Province from 2021–2024 using geographically weighted panel regression (GWPR) method. The dataset consists of secondary panel data compiled from the Ministry of Health and BPS-Statistics of East Nusa Tenggara Province, covering indicators across the health, social, economic, and environmental domains. Estimation was carried out through GWPR paired with an adaptive bisquare kernel weighting function. The resulting model demonstrates strong capacity to account for spatial heterogeneity in explaining toddler stunting rates, returning an value of and an AIC of . Analysis further yielded 15 regional groupings, each shaped by the variables found to be significant within individual regencies and cities. Variables confirmed to exert a significant influence on stunting rates include exclusive breastfeeding, vitamin A supplementation, infant and young child feeding, complete basic immunization, women's average years of schooling, prevalence of undernourishment, and poor population.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 ADINA NUR HALIMAH SANWANI, NI LUH PUTU SUCIPTAWATI, I GUSTI AYU MADE SRINADI

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

E-Jurnal Matematika (MTK) is licensed under a Creative Commons Attribution License (CC BY-NC 4.0)
