BayesMortalityPlus

CRANBayesMortalityPlusMaRDI QIDQ159206FDOQ159206

Bayesian Mortality Modelling

Author name not available (Why is that?)

Last update: 2 February 2024

Copyright license: GNU General Public License, version 3.0

Software version identifier: 0.1.0, 0.1.1, 0.2.2

Description

Fit Bayesian graduation mortality using the Heligman-Pollard model, as seen in Heligman, L., & Pollard, J. H. (1980) <doi:10.1017/S0020268100040257> and Dellaportas, Petros, et al. (2001) <doi:10.1111/1467-985X.00202>, and dynamic linear model (Campagnoli, P., Petris, G., and Petrone, S. (2009) <doi:10.1007/b135794_2>). While Heligman-Pollard has parameters with a straightforward interpretation yielding some rich analysis, the dynamic linear model provides a very flexible adjustment of the mortality curves by controlling the discount factor value. Closing methods for both Heligman-Pollard and dynamic linear model were also implemented according to Dodd, Erengul, et al. (2018) <https://www.jstor.org/stable/48547511>. The Bayesian Lee-Carter model is also implemented to fit historical mortality tables time series to predict the mortality in the following years and to do improvement analysis, as seen in Lee, R. D., & Carter, L. R. (1992) <doi:10.1080/01621459.1992.10475265> and Pedroza, C. (2006) <doi:10.1093/biostatistics/kxj024>.

Cites work

• Modeling and Forecasting U.S. Mortality
• The age pattern of mortality
• Bayesian Analysis of Mortality Data
• Dynamic linear models
• A Bayesian forecasting model: predicting U.S. male mortality

This page was built for software: BayesMortalityPlus