Spatial Geographically Weighted Regression (GWR) Model on Toddler Stunting in Java Island

Abstract

Stunting is a condition where a child fails to grow properly in height for their age caused by long term chronic malnutrition, repeated infection and insufficient of psychosocial stimulation. Children with stunting are prone to poor of cognitive development and intelligent, metabolic disease, and lack of immune systems to prevent chronic diseases such as diabetes and cancer. Java is one of the most populous island in Indonesia with high prevalent of stunting in 2021. The high population density results in less access to the right to a healthy life, triggering the problem of stunting. Therefore, it is important to conduct research to determine the factors that influence stunting toddlers in districts/cities on the island of Java. The different percentage of stunted toddlers in each district/city on the island of Java shows that there are differences in the characteristics of each region due to the factors behind it, causing spatial heterogeneity. Therefore, the appropriate method used in this study is Geographically Weighted Regression (GWR). GWR is one of the developments of multiple linear regression models that take into account the location of the region. Spatial influence is considered in the construction of GWR model. The results showed that there were six groups of districts/cities based on predictor variables that had a significant effect on stunting toddlers, then exclusive breastfeeding and proper sanitation became the dominant predictor variables that had a significant effect on stunting toddlers in all districts/cities in Java Island.