The increases in life expectancy over the last decades have strongly impacted the distribution of ages at death. Its parametric estimation can be complicated by cohort effects. Our addresses the issue by extending a recent three-component parametric model to include cohort effects in a Bayesian framework. The model is fit to male mortality data from five diverse Italian regions between 1974 and 2022. Our results demonstrate significant regional variations in mortality, influenced by cohort effects, particularly among cohorts born around World War I. The model effectively captures the evolution of mortality components, with cohort effects markedly improving fit of complex, even multi-modal curves.
Bayesian Modeling of Mortality in Italian Regions: A Three-Component Approach Incorporating Cohort Effects
Matteo Dimai
Primo
Methodology
;
2024-01-01
Abstract
The increases in life expectancy over the last decades have strongly impacted the distribution of ages at death. Its parametric estimation can be complicated by cohort effects. Our addresses the issue by extending a recent three-component parametric model to include cohort effects in a Bayesian framework. The model is fit to male mortality data from five diverse Italian regions between 1974 and 2022. Our results demonstrate significant regional variations in mortality, influenced by cohort effects, particularly among cohorts born around World War I. The model effectively captures the evolution of mortality components, with cohort effects markedly improving fit of complex, even multi-modal curves.Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
