PENERAPAN CROSS-VALIDATION PADA MODEL EFEK CAMPURAN: DAMPAK FAKTOR EKONOMI DAN KESEHATAN TERHADAP INDEKS KERENTANAN NEGARA-NEGARA DI ASIA TENGGARA

Abstract

This research aims to investigate the impact of economic growth on the stability of countries in Southeast Asia during the period 2010–2021. The research method involves the use of data from the International Monetary Fund (IMF), the World Health Organization (WHO), the World Bank, and the Fragile State Index (FSI). A mixed-effects model was used to analyze the relationship between these variables, and K-fold cross-validation was employed to determine the optimal subset model within the mixed-effects model framework. The research results indicate a model with quadratic nonlinear trend, produces lower root mean squared error (RMSE) and mean absolute error (MAE) values compared to other models, indicating a higher level of accuracy in predicting data. The conclusion of this research is that the mixed-effects model with a quadratic non-linear assumption, particularly the third model, exhibits superior predictive performance with an RMSE of 0.628 and MAE of 0.536. However, it should be highlighted that just a few variables, particularly life expectancy, GDP, and the square of GDP, contribute considerably to the variation in the mean FSI (Fragile States Index The findings provide insights into the model's ability to capture the complexity of relationships among predictor variables and mean FSI, as well as identify the variables influencing a country's vulnerability

Keywords

• kerapuhan negara, model efek-campuran, cross validation, asia tenggara
• fragile state, mixed-effect model, cross validation, south east asia