Exchangeable mortality projection

Vered Shapovalov; Zinoviy Landsman; Udi Makov

doi:10.1007/s13385-020-00255-w

Exchangeable mortality projection

Vered Shapovalov, Zinoviy Landsman, Udi Makov

Department of Statistics

Research output: Contribution to journal › Article › peer-review

Abstract

In this study we derive a novel multi-population Lee-Carter type model. Specifically, we extend the Bayesian model in Czado et al. (Insur Math Econ 36:260–284, 2005) to allow exchangeability between parameters of a group of m populations. In a validation-based examination, the proposed model is found to be beneficial for several examined countries. Also, we examine changes in forecasting ability due to varying calibration periods. Our results suggest that mortality rates from a distant past are inferior to those from a more recent past.

Original language	English
Pages (from-to)	113-133
Number of pages	21
Journal	European Actuarial Journal
Volume	11
Issue number	1
DOIs	https://doi.org/10.1007/s13385-020-00255-w
State	Published - Jun 2021

Bibliographical note

Publisher Copyright:
© 2021, EAJ Association.

Keywords

Bayesian
Lee–Carter methodology
Mortality forecasting
Multi-population model
Optimal calibration period
Validation-based approach

ASJC Scopus subject areas

Statistics and Probability
Economics and Econometrics
Statistics, Probability and Uncertainty

Access to Document

10.1007/s13385-020-00255-w

Cite this

@article{0669618bade248f280a3340912fb808f,

title = "Exchangeable mortality projection",

abstract = "In this study we derive a novel multi-population Lee-Carter type model. Specifically, we extend the Bayesian model in Czado et al. (Insur Math Econ 36:260–284, 2005) to allow exchangeability between parameters of a group of m populations. In a validation-based examination, the proposed model is found to be beneficial for several examined countries. Also, we examine changes in forecasting ability due to varying calibration periods. Our results suggest that mortality rates from a distant past are inferior to those from a more recent past.",

keywords = "Bayesian, Lee–Carter methodology, Mortality forecasting, Multi-population model, Optimal calibration period, Validation-based approach",

author = "Vered Shapovalov and Zinoviy Landsman and Udi Makov",

note = "Publisher Copyright: {\textcopyright} 2021, EAJ Association.",

year = "2021",

month = jun,

doi = "10.1007/s13385-020-00255-w",

language = "English",

volume = "11",

pages = "113--133",

journal = "European Actuarial Journal",

issn = "2190-9733",

publisher = "Springer International Publishing AG",

number = "1",

}

TY - JOUR

T1 - Exchangeable mortality projection

AU - Shapovalov, Vered

AU - Landsman, Zinoviy

AU - Makov, Udi

PY - 2021/6

Y1 - 2021/6

N2 - In this study we derive a novel multi-population Lee-Carter type model. Specifically, we extend the Bayesian model in Czado et al. (Insur Math Econ 36:260–284, 2005) to allow exchangeability between parameters of a group of m populations. In a validation-based examination, the proposed model is found to be beneficial for several examined countries. Also, we examine changes in forecasting ability due to varying calibration periods. Our results suggest that mortality rates from a distant past are inferior to those from a more recent past.

AB - In this study we derive a novel multi-population Lee-Carter type model. Specifically, we extend the Bayesian model in Czado et al. (Insur Math Econ 36:260–284, 2005) to allow exchangeability between parameters of a group of m populations. In a validation-based examination, the proposed model is found to be beneficial for several examined countries. Also, we examine changes in forecasting ability due to varying calibration periods. Our results suggest that mortality rates from a distant past are inferior to those from a more recent past.

KW - Bayesian

KW - Lee–Carter methodology

KW - Mortality forecasting

KW - Multi-population model

KW - Optimal calibration period

KW - Validation-based approach

UR - http://www.scopus.com/inward/record.url?scp=85100804087&partnerID=8YFLogxK

U2 - 10.1007/s13385-020-00255-w

DO - 10.1007/s13385-020-00255-w

M3 - Article

AN - SCOPUS:85100804087

SN - 2190-9733

VL - 11

SP - 113

EP - 133

JO - European Actuarial Journal

JF - European Actuarial Journal

IS - 1

ER -

Exchangeable mortality projection

Abstract

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this