Location–Scale Models in Demography: A Useful Re-parameterization of Mortality Models

Ugofilippo Basellini, Vladimir Canudas-Romo, Adam Lenart

Research output: Contribution to journalJournal articleResearchpeer-review

42 Downloads (Pure)

Abstract

Several parametric mortality models have been proposed to describe the age pattern of mortality since Gompertz introduced his “law of mortality” almost two centuries ago. However, very few attempts have been made to reconcile most of these models within a single framework. In this article, we show that many mortality models used in the demographic and actuarial literature can be re-parameterized in terms of a general and flexible family of models, the family of location–scale (LS) models. These models are characterized by two parameters that have a direct demographic interpretation: the location and scale parameters, which capture the shifting and compression dynamics of mortality changes, respectively. Re-parameterizing a model in terms of the LS family has several advantages over its classic formulation. In addition to aiding parameter interpretability and comparability, the statistical estimation of the LS parameters is facilitated due to their significantly lower correlation. The latter, in turn, further improves parameter interpretability and reduces estimation bias. We show the advantages of the LS family over the typical parameterization of mortality models with two illustrations using the Human Mortality Database.

Original languageEnglish
JournalEuropean Journal of Population
Volume35
Issue number4
Pages (from-to)645-673
ISSN0168-6577
DOIs
Publication statusPublished - 1. Oct 2019

Fingerprint

demography
mortality
interpretation
Law
trend

Keywords

  • Compression
  • Extreme–Value
  • Gamma–Gompertz
  • Law of mortality
  • Mortality modelling
  • Shifting

Cite this

@article{b2e878ac3ddf4bb3a4673fb1770c0c3a,
title = "Location–Scale Models in Demography: A Useful Re-parameterization of Mortality Models",
abstract = "Several parametric mortality models have been proposed to describe the age pattern of mortality since Gompertz introduced his “law of mortality” almost two centuries ago. However, very few attempts have been made to reconcile most of these models within a single framework. In this article, we show that many mortality models used in the demographic and actuarial literature can be re-parameterized in terms of a general and flexible family of models, the family of location–scale (LS) models. These models are characterized by two parameters that have a direct demographic interpretation: the location and scale parameters, which capture the shifting and compression dynamics of mortality changes, respectively. Re-parameterizing a model in terms of the LS family has several advantages over its classic formulation. In addition to aiding parameter interpretability and comparability, the statistical estimation of the LS parameters is facilitated due to their significantly lower correlation. The latter, in turn, further improves parameter interpretability and reduces estimation bias. We show the advantages of the LS family over the typical parameterization of mortality models with two illustrations using the Human Mortality Database.",
keywords = "Compression, Extreme–Value, Gamma–Gompertz, Law of mortality, Mortality modelling, Shifting",
author = "Ugofilippo Basellini and Vladimir Canudas-Romo and Adam Lenart",
year = "2019",
month = "10",
day = "1",
doi = "10.1007/s10680-018-9497-x",
language = "English",
volume = "35",
pages = "645--673",
journal = "European Journal of Population",
issn = "0168-6577",
publisher = "Springer",
number = "4",

}

Location–Scale Models in Demography : A Useful Re-parameterization of Mortality Models. / Basellini, Ugofilippo; Canudas-Romo, Vladimir; Lenart, Adam.

In: European Journal of Population, Vol. 35, No. 4, 01.10.2019, p. 645-673.

Research output: Contribution to journalJournal articleResearchpeer-review

TY - JOUR

T1 - Location–Scale Models in Demography

T2 - A Useful Re-parameterization of Mortality Models

AU - Basellini, Ugofilippo

AU - Canudas-Romo, Vladimir

AU - Lenart, Adam

PY - 2019/10/1

Y1 - 2019/10/1

N2 - Several parametric mortality models have been proposed to describe the age pattern of mortality since Gompertz introduced his “law of mortality” almost two centuries ago. However, very few attempts have been made to reconcile most of these models within a single framework. In this article, we show that many mortality models used in the demographic and actuarial literature can be re-parameterized in terms of a general and flexible family of models, the family of location–scale (LS) models. These models are characterized by two parameters that have a direct demographic interpretation: the location and scale parameters, which capture the shifting and compression dynamics of mortality changes, respectively. Re-parameterizing a model in terms of the LS family has several advantages over its classic formulation. In addition to aiding parameter interpretability and comparability, the statistical estimation of the LS parameters is facilitated due to their significantly lower correlation. The latter, in turn, further improves parameter interpretability and reduces estimation bias. We show the advantages of the LS family over the typical parameterization of mortality models with two illustrations using the Human Mortality Database.

AB - Several parametric mortality models have been proposed to describe the age pattern of mortality since Gompertz introduced his “law of mortality” almost two centuries ago. However, very few attempts have been made to reconcile most of these models within a single framework. In this article, we show that many mortality models used in the demographic and actuarial literature can be re-parameterized in terms of a general and flexible family of models, the family of location–scale (LS) models. These models are characterized by two parameters that have a direct demographic interpretation: the location and scale parameters, which capture the shifting and compression dynamics of mortality changes, respectively. Re-parameterizing a model in terms of the LS family has several advantages over its classic formulation. In addition to aiding parameter interpretability and comparability, the statistical estimation of the LS parameters is facilitated due to their significantly lower correlation. The latter, in turn, further improves parameter interpretability and reduces estimation bias. We show the advantages of the LS family over the typical parameterization of mortality models with two illustrations using the Human Mortality Database.

KW - Compression

KW - Extreme–Value

KW - Gamma–Gompertz

KW - Law of mortality

KW - Mortality modelling

KW - Shifting

U2 - 10.1007/s10680-018-9497-x

DO - 10.1007/s10680-018-9497-x

M3 - Journal article

C2 - 31656456

VL - 35

SP - 645

EP - 673

JO - European Journal of Population

JF - European Journal of Population

SN - 0168-6577

IS - 4

ER -