Semi-parametric accelerated hazard relational models with applications to mortality projections

Cadena, Meitner; Denuit, Michel

doi:10.1016/j.insmatheco.2016.02.003

Cited by 7 publications

(3 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Considering these works, we can see that the stated results are not specific to the Lee-Carter model but generally hold true as soon as the conditional survival probabilities are monotonic functions of the time index. This applies for instance to the new approach proposed by Cadena and Denuit (2015). In this section, we derive similar approximations for our specification (2.2)-(2.3).…”

Section: Perfectly Dependent Departures From the Common Trendmentioning

confidence: 68%

From regulatory life tables to stochastic mortality projections: The exponential decline model

Denuit

Trufin

2016

Insurance: Mathematics and Economics

Self Cite

View full text Add to dashboard Cite

Often in actuarial practice, mortality projections are obtained by letting age-specific death rates decline exponentially at their own rate. Many life tables used for annuity pricing are built in this way. The present paper adopts this point of view and proposes a simple and powerful mortality projection model in line with this elementary approach, based on the recently studied mortality improvement rates. Two main applications are considered. First, as most reference life tables produced by regulators are deterministic by nature, they can be made stochastic by superposing random departures from the assumed age-specific trend, with a volatility calibrated on market or portfolio data. This allows the actuary to account for the systematic longevity risk in solvency calculations. Second, the model can be fitted to historical data and used to produce longevity forecasts. A number of conservative and tractable approximations are derived to provide the actuary with reasonably accurate approximations for various relevant quantities, available at limited computational cost. Besides applications to stochastic mortality projection models, we also derive useful properties involving supermodular, directionally convex and stop-loss orders.

show abstract

Section: Perfectly Dependent Departures From the Common Trendmentioning

confidence: 68%

From regulatory life tables to stochastic mortality projections: The exponential decline model

Denuit

Trufin

2016

Insurance: Mathematics and Economics

Self Cite

View full text Add to dashboard Cite

show abstract

“…The approach allows choosing the parametric specification for the underlying dependent variable and significantly improves the model when the selected parametric form adequately mimics the empirical one (Orbe et al, 2002). AFT models have found applications in many areas of research including, e.g., for investigating the risk factors affecting Alzheimer's disease (Lee et al, 2017), for mortality projections (Cadena and Denuit, 2016) and for analyzing the incident duration on freeways, i.e. the time from the occurrence of an incident to road clearance (Junhua et al, 2013).…”

Section: Model Setup and Mle Estimationmentioning

confidence: 99%

Duration of long-term care: Socio-economic factors, type of care interactions and evolution

Fuino

Wagner

2020

Insurance: Mathematics and Economics

View full text Add to dashboard Cite

“…Our methodology is also inspired by the model proposed by Camarda et al (2008) to analyse mortality developments from age-at-death distributions by transforming the age axis with a smooth non-linear warping function. Furthermore, Cadena and Denuit (2016) recently introduced an accelerated hazard relational model based on a smooth transformation of the age scale free of monotonic constraints, and they used it to estimate and project mortality in Belgium. The STAD model has elements that are common to both approaches, but it is also significantly different.…”

Section: Forecasts To 2040mentioning

confidence: 99%

Modelling and forecasting adult age-at-death distributions

Basellini

Camarda

2019

Population Studies

View full text Add to dashboard Cite

Age-at-death distributions provide an informative description of the mortality pattern of a population, but they have generally been neglected for modelling and forecasting mortality. In this article, we use the distribution of deaths to model and forecast adult mortality. In particular, we introduce a relational model that relates a fixed "standard" to a series of observed distributions by a transformation of the age axis. The proposed Segmented Transformation Age-at-death Distributions (STAD) model is parsimonious and efficient: using only three parameters, it captures and disentangles mortality developments in terms of shifting and compression dynamics of mortality. In addition, mortality forecasts can be derived from parameters' extrapolation using time series models. We illustrate and compare our methodology with the Lee-Carter model and its variants for females in four high-longevity countries. We show that the STAD fits very well the observed mortality pattern, and that its forecasts are more accurate and optimistic than the Lee-Carter variants.

show abstract

Semi-parametric accelerated hazard relational models with applications to mortality projections

Cited by 7 publications

References 17 publications

From regulatory life tables to stochastic mortality projections: The exponential decline model

From regulatory life tables to stochastic mortality projections: The exponential decline model

Duration of long-term care: Socio-economic factors, type of care interactions and evolution

Modelling and forecasting adult age-at-death distributions

Contact Info

Product

Resources

About