Segmentation of toddler nutritional status using REBUS and FIMIX partial least square in Southeast Sulawesi

Nutrition is one of the important factors that play a major role in the growth and development of children so that they can develop optimally. Child malnutrition, such as stunting, underweight, and wasting, is a significant problem in Indonesia. The World Health Organization (WHO) determined that the nutritional status of children under five in Indonesia is in the chronic category, one of which is in Southeast Sulawesi Province. This study examines and analyzes the factors that influence the nutritional status of children under five in Southeast Sulawesi using the Partial Least Square Structural Equation Modeling (SEM-PLS) method and then segments the nutritional status of children under five using Response Based Unit Segmentation Modeling in Partial Least Square (REBUS-PLS) and Finite Mixture Partial Least Square (FIMIX-PLS). The number of observations in this study was 216 sub-districts. From the results of the SEM-PLS analysis conducted, it was concluded that the 10 indicators used were valid and significant in describing the latent variables, and the practice factor variable had an effect on the food factor variable, the food factor variable had an effect on the service factor variable, and the service factor variable had an effect on the under-five nutritional status variable. The REBUS-PLS analysis results in two segments, with one segment of 75 observations and the other segment of 141 observations. The same conclusion is obtained as in the SEM-PLS analysis, but the results of the analysis with REBUS-PLS have a greater value than the results of the SEM-PLS analysis. Key points of the article: 1. Comparing REBUS-PLS and FIMIX-PLS methods for overcoming the case of heterogeneity in dat. 2. Combining the SEM-PLS method with the REBUS and FIMIX methods in discussing the factors that influence the nutritional status of children under five in Southeast Sulawesi.