Modeling Longevity Risk With Generalized Dynamic Factor Models and Vine-Copulae

Chuliá, Helena; Guillén, Montserrat; Uribe, Jorge M.

doi:10.1017/asb.2015.21

Cited by 14 publications

(17 citation statements)

References 59 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Esto ha sido explorado en épocas recientes en la literatura actuarial (Chuliá, Guillén & Uribe, 2016) llevando a la exploración de propuestas alternativas de pronóstico, que en algunos contextos superan al modelo original. No obstante, una de las ventajas del méto-do utilizado aquí es que permite el pronóstico de tasas que son coherentes entre sí, al depender de una misma tendencia estocástica subyacente.…”

Section: Conclusiones Y Futuras Extensionesunclassified

Tablas de vida de Santiago de Cali: Tendencias recientes y proyecciones: 1985-2030

Gil

Marío²

2017

soc.eco

View full text Add to dashboard Cite

Este trabajo está bajo la licencia Creative Commons Attribution 3.0 ResumenEl objetivo de este documento es exponer las tendencias de mortalidad recientes en hombres y mujeres, en Santiago de Cali, construidas mediante la aplicación del modelo de Lee y Carter (1992). También aportar a la literatura y agencias de política regionales proyecciones futuras de las tasas de mortalidad específicas en la ciudad, a través de técnicas de uso común en las literaturas actuarial y demográfica contemporáneas. Los patrones de mortalidad en Cali se ajustan en buena medida a los hallazgos para otras regiones del mundo. Se han presentado importantes reducciones en la mayor parte de las tasas de mortalidad específicas durante el período analizado y se pronostican, por ende, futuras reducciones para casi todos los grupos de edad, exceptuando los hombres entre 15 y 25 años.Palabras clave: tasas-mortalidad; pronóstico; Lee-Carter; Santiago de Cali. AbstractThis paper explores recent mortality trends in men and women, in Santiago de Cali. To this end, the model proposed by Lee and Cater (1992) is fitted to the data. Through techniques commonly used in contemporary actuarial and demographic literatures, this article also provides future projections of specific mortality rates, which may be useful for the literature and regional policy agencies. The mortality patterns documented here are in line we previous findings for other regions in the world. Important reductions in most of the mortality rates have occurred during the sample period and, therefore, future reductions in mortality rates are expected, in almost all the age-ranges, excepting men between 15 and 25 years.

show abstract

Section: Conclusiones Y Futuras Extensionesunclassified

Tablas de vida de Santiago de Cali: Tendencias recientes y proyecciones: 1985-2030

Gil

Marío²

2017

soc.eco

View full text Add to dashboard Cite

show abstract

“…These models were generated based on a diverse spectrum of mortality rate projections tools. Some of the models involved application of life tables [6] [7], stochastic mortality models [8], generalized dynamic factor models with vine-copulae simulations [9]; and various data mining techniques including logistic regression technique and decision tree technique [10] [11].…”

Section: Introductionmentioning

confidence: 99%

Ranking System for Ordinal Longevity Risk Factors using Proportional-Odds Logistic Regression

Hanafi¹,

Nohuddin²

2020

IJACSA

View full text Add to dashboard Cite

Longevity improvements have traditionally been analysed and extrapolated for future actuarial projections of longevity risk by using a range of statistical methods with different combinations of statistical data types. These methods have shown great performances in explaining the trend movements of the longevity rate. However, actuaries believe that knowing the trend movements is not enough, especially in controlling the impact of the longevity risk. Accessing the effects of each level of the risk factors, especially ordinal risk factors, towards the improvements of the longevity rate would provide significant additional knowledge to the trend movements. Therefore, this study was conducted to determine the potentiality of Proportional-Odds Logistics Regression in ranking the levels of the ordinal risk factors based on their effects on longevity improvements. Based on the results, this method has successfully reordered the levels of each risk factor to be according to their effects in improving longevity rate. Hence, a more meaningful ranking system has been developed based on these new ordered risk factors. This new ranking system will help in improving the ability of any statistical methods in projecting the longevity risk when handling ordinal variables.

show abstract

“…However, VECM only captures linear and symmetric dependence in time and between series, and therefore can be restrictive in a high-dimensional case where dependence structure is complex. Wang et al (2015), Chen et al (2015), Chuliá et al (2016) and Chen et al (2017) proposed the application of multivariate copulas to capture a wider range of mortality dependence. More specifically, to model mortality dependence Chen et al (2015) used a static one-factor copula in which the factor is common among all population groups.…”

Section: Introductionmentioning

confidence: 99%

“…Wang et al (2015) considered elliptical and Archimedean copulas with time-varying parameters. Chuliá et al (2016) fitted generalized dynamic factor models to the differences of the log-mortality rates. Chen et al (2017) improved the work of Chen et al (2015) by adding a country-specific factor and allowing copula parameters to vary with time.…”

Section: Introductionmentioning

confidence: 99%

“…The only application of vine copula in mortality modelling was conducted by Chuliá et al (2016), in which a dynamic factor copula is fitted to mortality improvement rates and then a vine copula, nested under the factor copula, is used to model the dependence between idiosyncratic factors. In this paper, we use vine copula as the main dependence structure.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Modelling Mortality Dependence With Regime-Switching Copulas

Zhou¹

2019

ASTIN Bull.

View full text Add to dashboard Cite

We propose a two-regime Markov switching copula to depict the evolution of mortality dependence. One regime represents periods of high dependence and the other regime represents periods of low dependence. Each regime features a regular vine (R-vine) copula that, built on bivariate copulas, provides great flexibility for modelling complex high-dimensional dependence. Our estimated model indicates that the years of recovery from extreme mortality deterioration and the years of health care reform more likely fall into the low regime, while the years in which extreme mortality deteriorating events break out and the peaceful years without major mortality-impacting events more likely fall into the high regime. We use a case study to illustrate how the regime-switching copula can be applied to assess the effectiveness of longevity risk hedge with different beliefs about future mortality dependence evolution incorporated.

show abstract

Modeling Longevity Risk With Generalized Dynamic Factor Models and Vine-Copulae

Cited by 14 publications

References 59 publications

Tablas de vida de Santiago de Cali: Tendencias recientes y proyecciones: 1985-2030

Tablas de vida de Santiago de Cali: Tendencias recientes y proyecciones: 1985-2030

Ranking System for Ordinal Longevity Risk Factors using Proportional-Odds Logistic Regression

Modelling Mortality Dependence With Regime-Switching Copulas

Contact Info

Product

Resources

About