This short note supplements the paper by Glschössl et al. (Eur Actuar J 1:23–41, 2011) with an efficient method allowing actuaries to include continuous covariates in their life tables, such as the sum insured for instance. Compared to the classical approach based on grouped data adopted in the majority of actuarial mortality studies, individual observations recorded at the policy level are included in the Poisson regression model. The proposed procedure avoids any preliminary, subjective banding of the range of continuous covariates that may bias the resulting life tables. The approach is illustrated on a numerical example demonstrating its advantages when individual mortality data are available.
Life tables Poisson regression GLM GAM
This is a preview of subscription content, log in to check access
The authors wish to express their gratitude to the anonymous referee and the editor for useful suggestions that greatly helped to improve a previous version of this text. The present work originated from interesting discussions with Jérémy Goris, Marine Habart and Tom Popa from the Retirement and Pension Funds team of the AXA Group, based in Paris, France. The authors wish to thank the AXA team for these fruitful interactions that have inspired the present note to a large extent.
Brouhns N, Denuit M, Vermunt JK (2002) A Poisson log-bilinear approach to the construction of projected life tables. Insur Math Econ 31:373–393CrossRefMATHGoogle Scholar
Fong JH (2015) Beyond age and sex: enhancing annuity pricing. Geneva Risk Insur Rev 40:133–170CrossRefGoogle Scholar
Glschössl S, Schoenmaekers P, Denuit M (2011) Risk classification in life insurance: methodology and case study. Eur Actuar J 1:23–41MathSciNetCrossRefGoogle Scholar
Guibert Q, Planchet F (2014) Construction de lois d’expérience en présence d’évènements concurrents: application à l’estimation des lois d’incidence d’un contrat dépendance. Bulletin Français d’Actuariat 14:5–28Google Scholar
Klein N, Denuit M, Lang S, Kneib Th (2014) Nonlife ratemaking and risk management with Bayesian additive models for location, scale and shape. Insur Math Econ 55:225–249MathSciNetCrossRefMATHGoogle Scholar