Uncertainty in mortality forecasting an extension to the classical Lee-Carter approach.

*(English)*Zbl 1203.91113Summary: Traditionally, actuaries have modeled mortality improvement using deterministic reduction factors, with little consideration of the associated uncertainty. As mortality improvement has become an increasingly significant source of financial risk, it has become important to measure the uncertainty in the forecasts. Probabilistic confidence intervals provided by the widely accepted Lee-Carter model are known to be excessively narrow, due primarily to the rigid structure of the model. In this paper, we relax the model structure by considering individual differences (heterogeneity) in each age-period cell. The proposed extension not only provides a better goodness-of-fit based on standard model selection criteria, but also ensures more conservative interval forecasts of central death rates and hence can better reflect the uncertainty entailed. We illustrate the results using US and Canadian mortality data.

##### MSC:

91B30 | Risk theory, insurance (MSC2010) |

62P05 | Applications of statistics to actuarial sciences and financial mathematics |

91D20 | Mathematical geography and demography |

PDF
BibTeX
XML
Cite

\textit{J. S. H. Li} et al., ASTIN Bull. 39, No. 1, 137--164 (2009; Zbl 1203.91113)

Full Text:
DOI

##### References:

[1] | Insurance: Mathematics and Economics 27 pp 313– (2000) |

[2] | North American Actuarial Journal (2009) |

[3] | North American Actuarial Journal 2 pp 24– (2003) |

[4] | Scandinavian Actuarial Journal 31 pp 212– (2005) |

[5] | Computational Methods for Fitting and Extrapolating the Lee-Carter Model of Mortality Change (1993) |

[6] | Insurance: Mathematics and Economics 31 pp 373– (2002) |

[7] | Neonatal and Perinatal Mortality: Country, Regional and Global Estimates (2006) |

[8] | DOI: 10.2307/2530689 · Zbl 0611.62136 |

[9] | Time Series Analysis Forecasting and Control (1976) |

[10] | Journal of Actuarial Practice 6 pp 221– (1998) |

[11] | DOI: 10.1080/00324720215935 |

[12] | DOI: 10.2307/2061224 |

[13] | Journal of Official Statistics 13 pp 279– (1997) |

[14] | DOI: 10.1038/35015561 |

[15] | IEEE Transactions on Automatic Control AC–19 pp 716– (1974) |

[16] | DOI: 10.1214/aos/1176344136 · Zbl 0379.62005 |

[17] | Simulation, 3rd edition (2003) |

[18] | Insurance: Mathematics and Economics 38 pp 556– (2006) |

[19] | Insurance: Mathematics and Economics 33 pp 255– (2003) |

[20] | DOI: 10.1080/10920277.2006.10597413 |

[21] | Infant mortality by birthweight and other characteristics: United States, 1985 birth cohort pp 94– (1994) |

[22] | DOI: 10.2307/2061263 |

[23] | Generalized Linear Models, 2nd edition (1989) |

[24] | Scandinavian Actuarial Journal 31 pp 187– (2005) |

[25] | Journal of the American Statistical Association 87 pp 659– (1992) |

[26] | Demography 28 pp 537– (2001) |

[27] | DOI: 10.1177/0027950105061498 |

[28] | Loss Models: from Data to Decisions (2004) |

[29] | Determining Comparable Levels of Functional Disability (1998) |

[30] | DOI: 10.1093/biomet/71.1.75 · Zbl 0553.92013 |

[31] | Backtesting Stochastic Mortality Models: An Ex-Post Evaluation of Multi-Period-Ahead Density Forecasts (2008) |

[32] | Applied Stochastic Models in Business and Industry (2007) |

[33] | Insurance: Mathematics and Economics 36 pp 260– (2005) |

[34] | DOI: 10.1191/1471082X04st080oa · Zbl 1061.62171 |

[35] | DOI: 10.1093/biomet/70.1.269 · Zbl 0511.62007 |

[36] | Long-Term Budgetary Pressures and Policy Options (1998) |

[37] | Mortality by Occupation, Industry, and Cause of Death: 24 Reporting States (1984-1988) |

This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. It attempts to reflect the references listed in the original paper as accurately as possible without claiming the completeness or perfect precision of the matching.