A continuous-time stochastic model for the mortality surface of multiple populations

Petar Jevtic, Luca Regis

Research output: Contribution to journalArticle

Abstract

We formulate, study and calibrate a continuous-time model for the joint evolution of the mortality surface of multiple populations. We model the mortality intensity by age and population as a mixture of stochastic latent factors, that can be either population-specific or common to all populations. These factors are described by affine time-(in)homogeneous stochastic processes. Traditional, deterministic mortality laws can be extended to multi-population stochastic counterparts within our framework. We detail the calibration procedure when factors are Gaussian, using centralized data-fusion Kalman filter. We provide an application based on the joint mortality of UK and Dutch males and females. Although parsimonious, the specification we calibrate provides a good fit of the observed mortality surface (ages 0–89) of both sexes and populations between 1960 and 2013.

Original languageEnglish (US)
Pages (from-to)181-195
Number of pages15
JournalInsurance: Mathematics and Economics
Volume88
DOIs
StatePublished - Sep 1 2019

Fingerprint

Continuous-time Model
Mortality
Stochastic Model
Data Fusion
Kalman Filter
Continuous time
Stochastic model
Stochastic Processes
Calibration
Specification

Keywords

  • Centralized data fusion
  • Continuous-time stochastic mortality
  • Kalman filter estimation
  • Mortality surface
  • Multi-population mortality

ASJC Scopus subject areas

  • Statistics and Probability
  • Economics and Econometrics
  • Statistics, Probability and Uncertainty

Cite this

A continuous-time stochastic model for the mortality surface of multiple populations. / Jevtic, Petar; Regis, Luca.

In: Insurance: Mathematics and Economics, Vol. 88, 01.09.2019, p. 181-195.

Research output: Contribution to journalArticle

@article{2912981d76ac420ba461eaeb6eac2674,
title = "A continuous-time stochastic model for the mortality surface of multiple populations",
abstract = "We formulate, study and calibrate a continuous-time model for the joint evolution of the mortality surface of multiple populations. We model the mortality intensity by age and population as a mixture of stochastic latent factors, that can be either population-specific or common to all populations. These factors are described by affine time-(in)homogeneous stochastic processes. Traditional, deterministic mortality laws can be extended to multi-population stochastic counterparts within our framework. We detail the calibration procedure when factors are Gaussian, using centralized data-fusion Kalman filter. We provide an application based on the joint mortality of UK and Dutch males and females. Although parsimonious, the specification we calibrate provides a good fit of the observed mortality surface (ages 0–89) of both sexes and populations between 1960 and 2013.",
keywords = "Centralized data fusion, Continuous-time stochastic mortality, Kalman filter estimation, Mortality surface, Multi-population mortality",
author = "Petar Jevtic and Luca Regis",
year = "2019",
month = "9",
day = "1",
doi = "10.1016/j.insmatheco.2019.07.001",
language = "English (US)",
volume = "88",
pages = "181--195",
journal = "Insurance: Mathematics and Economics",
issn = "0167-6687",
publisher = "Elsevier",

}

TY - JOUR

T1 - A continuous-time stochastic model for the mortality surface of multiple populations

AU - Jevtic, Petar

AU - Regis, Luca

PY - 2019/9/1

Y1 - 2019/9/1

N2 - We formulate, study and calibrate a continuous-time model for the joint evolution of the mortality surface of multiple populations. We model the mortality intensity by age and population as a mixture of stochastic latent factors, that can be either population-specific or common to all populations. These factors are described by affine time-(in)homogeneous stochastic processes. Traditional, deterministic mortality laws can be extended to multi-population stochastic counterparts within our framework. We detail the calibration procedure when factors are Gaussian, using centralized data-fusion Kalman filter. We provide an application based on the joint mortality of UK and Dutch males and females. Although parsimonious, the specification we calibrate provides a good fit of the observed mortality surface (ages 0–89) of both sexes and populations between 1960 and 2013.

AB - We formulate, study and calibrate a continuous-time model for the joint evolution of the mortality surface of multiple populations. We model the mortality intensity by age and population as a mixture of stochastic latent factors, that can be either population-specific or common to all populations. These factors are described by affine time-(in)homogeneous stochastic processes. Traditional, deterministic mortality laws can be extended to multi-population stochastic counterparts within our framework. We detail the calibration procedure when factors are Gaussian, using centralized data-fusion Kalman filter. We provide an application based on the joint mortality of UK and Dutch males and females. Although parsimonious, the specification we calibrate provides a good fit of the observed mortality surface (ages 0–89) of both sexes and populations between 1960 and 2013.

KW - Centralized data fusion

KW - Continuous-time stochastic mortality

KW - Kalman filter estimation

KW - Mortality surface

KW - Multi-population mortality

UR - http://www.scopus.com/inward/record.url?scp=85069730776&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85069730776&partnerID=8YFLogxK

U2 - 10.1016/j.insmatheco.2019.07.001

DO - 10.1016/j.insmatheco.2019.07.001

M3 - Article

AN - SCOPUS:85069730776

VL - 88

SP - 181

EP - 195

JO - Insurance: Mathematics and Economics

JF - Insurance: Mathematics and Economics

SN - 0167-6687

ER -