Variable selection in finite mixture of regression models with an unknown number of components

A Bayesian framework for finite mixture models to deal with model selection and the selection of the number of mixture components simultaneously is presented. For that purpose, a feasible reversible jump Markov Chain Monte Carlo algorithm is proposed to model each component as a sparse regression model. This approach is made robust to outliers by using a prior that induces heavy tails and works well under multicollinearity and with high-dimensional data. Finally, the framework is applied to cross-sectional data investigating early warning indicators. The results reveal two distinct country groups for which estimated effects of vulnerability indicators vary considerably.