Implementing social and economic policies addressing the gender longevity gap should be guided by quantitative analyses about how such a gap is expected to evolve over time. The performance of the Lee-Carter (LC) model is investigated to fit the gender gap ratio (GGR), namely the ratio of male death rates to female ones. The analysis is based on the use of a Cox-Ingersoll-Ross (CIR) process to describe the fitting errors of the LC model. In particular, the long-term mean and the volatility of such a process drive the analysis as they are indicators of the long-term fitting attitude of the LC model along with the overall risk of such a model. Systematic evidence is provided on the LC model performance in estimating GGR trends across ages and on a sample of 25 countries, also by making use of functional cluster analysis.
Lee-Carter model: Biases and risk in the estimation of the gender mortality gap
Giovanna Apicella;
2024-01-01
Abstract
Implementing social and economic policies addressing the gender longevity gap should be guided by quantitative analyses about how such a gap is expected to evolve over time. The performance of the Lee-Carter (LC) model is investigated to fit the gender gap ratio (GGR), namely the ratio of male death rates to female ones. The analysis is based on the use of a Cox-Ingersoll-Ross (CIR) process to describe the fitting errors of the LC model. In particular, the long-term mean and the volatility of such a process drive the analysis as they are indicators of the long-term fitting attitude of the LC model along with the overall risk of such a model. Systematic evidence is provided on the LC model performance in estimating GGR trends across ages and on a sample of 25 countries, also by making use of functional cluster analysis.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
