A Comparative Study of Penalised, Bayesian, Spatial, and Tree-Based Models for Provincial Poverty in Indonesia: Small Samples and High Collinearity
This study addresses the challenges of analyzing provincial poverty in Indonesia, where a small sample size (n = 34) and high-dimensional multicollinearity undermine the stability of conventional regression models. To tackle this, the authors develop a systematic comparative framework evaluating several regularization and machine learning approaches—including ridge regression, LASSO, elastic net, Bayesian shrinkage priors, spatial ICAR, and Bayesian additive regression trees (BART)—in terms of predictive performance and robustness. The results demonstrate that parametric linear shrinkage methods, particularly ridge regression, yield the most accurate and stable predictions, whereas more complex ensemble models tend to overfit. Notably, ICT skills emerge as a consistently significant negative predictor of poverty across all well-performing models, highlighting their potential as a strategic priority for development policy. This work offers a reliable modeling paradigm and empirical foundation for evidence-based policymaking in data-scarce settings.