Multilevel cluster-weighted models for the evaluation of hospital

In recent years, increasing attention has been directed toward problems inherentto quality control in healthcare services. In particular, it is necessary to measure effectiveness with respect to improving healthcare outcomes of diagnostic procedures or specific treatmentepisodes. The performance of hospitals is usually evaluated by multilevel models and other methods for risk adjustment. However, these approaches are not suitable for data with largeunobserved heterogeneity. A potentially large source of unobserved heterogeneity comesfrom the variation of the regression coefficients between groups of individuals sharing similarbut unobserved characteristics. To overcome such drawbacks, we propose the multilevelcluster-weighted model, a new mixture model approach for handling hierarchical data.