Survival analysis of pension scheme mortality when data are missing

Francesco Ungolo; Marcus C. Christiansen; Torsten Kleinow; Angus S. Macdonald

doi:10.1080/03461238.2019.1580610

Survival analysis of pension scheme mortality when data are missing

Francesco Ungolo, Marcus C. Christiansen, Torsten Kleinow, Angus S. Macdonald

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

5 Citations (Scopus)

118 Downloads (Pure)

Abstract

Missing data is a problem that may be faced by actuaries when analysing mortality data. In this paper we deal with pension scheme data, where the future lifetime of each member is modelled by means of parametric survival models incorporating covariates, which may be missing for some individuals. Parameters are estimated by likelihood-based techniques. We analyse statistical issues, such as parameter identifiability, and propose an algorithm to handle the estimation task. Finally, we analyse the financial impact of including covariates maximally, compared with excluding parts of the mortality experience where data are missing; in particular we consider annuity factors and mis-estimation risk capital requirements.

Original language	English
Pages (from-to)	523-547
Number of pages	25
Journal	Scandinavian Actuarial Journal
Volume	2019
Issue number	6
Early online date	27 Feb 2019
DOIs	https://doi.org/10.1080/03461238.2019.1580610
Publication status	Published - 3 Jul 2019

Keywords

Mortality
longevity risk
missing data
mortality models with covariates
survival model

ASJC Scopus subject areas

Statistics and Probability
Economics and Econometrics
Statistics, Probability and Uncertainty

Access to Document

10.1080/03461238.2019.1580610

Download pdf
This is an Accepted Manuscript of an article published by Taylor & Francis in Scandinavian Actuarial Journal on 27/2/2019, available online: http://www.tandfonline.com/10.1080/03461238.2019.1580610
Accepted author manuscript, 560 KB

Cite this

@article{668d35beae5a45659f9238f2925f3185,

title = "Survival analysis of pension scheme mortality when data are missing",

abstract = "Missing data is a problem that may be faced by actuaries when analysing mortality data. In this paper we deal with pension scheme data, where the future lifetime of each member is modelled by means of parametric survival models incorporating covariates, which may be missing for some individuals. Parameters are estimated by likelihood-based techniques. We analyse statistical issues, such as parameter identifiability, and propose an algorithm to handle the estimation task. Finally, we analyse the financial impact of including covariates maximally, compared with excluding parts of the mortality experience where data are missing; in particular we consider annuity factors and mis-estimation risk capital requirements.",

keywords = "Mortality, longevity risk, missing data, mortality models with covariates, survival model",

author = "Francesco Ungolo and Christiansen, {Marcus C.} and Torsten Kleinow and Macdonald, {Angus S.}",

year = "2019",

month = jul,

day = "3",

doi = "10.1080/03461238.2019.1580610",

language = "English",

volume = "2019",

pages = "523--547",

journal = "Scandinavian Actuarial Journal",

issn = "0346-1238",

publisher = "Taylor & Francis",

number = "6",

}

TY - JOUR

T1 - Survival analysis of pension scheme mortality when data are missing

AU - Ungolo, Francesco

AU - Christiansen, Marcus C.

AU - Kleinow, Torsten

AU - Macdonald, Angus S.

PY - 2019/7/3

Y1 - 2019/7/3

N2 - Missing data is a problem that may be faced by actuaries when analysing mortality data. In this paper we deal with pension scheme data, where the future lifetime of each member is modelled by means of parametric survival models incorporating covariates, which may be missing for some individuals. Parameters are estimated by likelihood-based techniques. We analyse statistical issues, such as parameter identifiability, and propose an algorithm to handle the estimation task. Finally, we analyse the financial impact of including covariates maximally, compared with excluding parts of the mortality experience where data are missing; in particular we consider annuity factors and mis-estimation risk capital requirements.

AB - Missing data is a problem that may be faced by actuaries when analysing mortality data. In this paper we deal with pension scheme data, where the future lifetime of each member is modelled by means of parametric survival models incorporating covariates, which may be missing for some individuals. Parameters are estimated by likelihood-based techniques. We analyse statistical issues, such as parameter identifiability, and propose an algorithm to handle the estimation task. Finally, we analyse the financial impact of including covariates maximally, compared with excluding parts of the mortality experience where data are missing; in particular we consider annuity factors and mis-estimation risk capital requirements.

KW - Mortality

KW - longevity risk

KW - missing data

KW - mortality models with covariates

KW - survival model

UR - http://www.scopus.com/inward/record.url?scp=85062327578&partnerID=8YFLogxK

U2 - 10.1080/03461238.2019.1580610

DO - 10.1080/03461238.2019.1580610

M3 - Article

SN - 0346-1238

VL - 2019

SP - 523

EP - 547

JO - Scandinavian Actuarial Journal

JF - Scandinavian Actuarial Journal

IS - 6

ER -

Survival analysis of pension scheme mortality when data are missing

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this