GLMM AND GLMM TREE METHODS FOR MODELING STUNTING PREVALENCE IN WEST JAVA

Abstract

This study compares the Generalized Linear Mixed Model (GLMM) and GLMM Tree methods in modeling stunting prevalence in West Java. Stunting is a significant public health issue, especially in developing regions, and accurate measurement is crucial for effective intervention. GLMM is a statistical method commonly used to handle hierarchical data and account for inter-group variability. At the same time, the GLMM Tree is a newer method that combines mixed models with decision tree approaches to capture complex and heterogeneous data structures. The study uses stunting data from various districts in West Java and applies both methods to evaluate their accuracy in predicting stunting prevalence. The analysis results indicate that each method has its advantages depending on the complexity and heterogeneity of the data. GLMM performs better in situations with clear and homogeneous data structures, whereas GLMM Tree performs better in heterogeneous and complex data conditions.