Búsqueda

Bivariate phase-type distributions for experience rating in disability insurance

Sección: Artículos
Título: Bivariate phase-type distributions for experience rating in disability insurance / Christian Furrer, Jacob Juhl Sørensen and Jorge YslasAutor: Furrer, Christian
Notas: Sumario: The article develops advanced mixed Poisson regression models applied to experience rating in disability insurance. It introduces hierarchical gamma distributions and multivariate phase-type distributions to model heterogeneity and dependence between disability and recovery rates. Estimation algorithms based on EM and ECM are presented, together with a simulation study comparing the predictive performance of the different approaches. The results show that phase-type models offer greater flexibility and improved predictive performance, especially when complex dependencies exist between latent group effectsRegistros relacionados: En: European Actuarial Journal. - Cham, Switzerland : Springer Nature Switzerland AG, 2021-2022. - 13/04/2026 Número 16 issue 1 - abril 2026 , 37 p.Materia / lugar / evento: Seguro de incapacidad Tarificación Modelos actuariales Riesgo aleatorio Rendimiento Otros autores: Sørensen, Jacob Juhl Yslas, Jorge Springer Otras clasificaciones: 11