Smoothing dispersed counts with applications to mortality data

Iain David Currie, Viani Djeundje Biatat

Research output: Contribution to journalArticle

Abstract

Mortality data are often classified by age at death and year of death. This classification results in a heterogeneous risk set and this can cause problems for the estimation and forecasting of mortality. In the modelling of such data, we replace the classical assumption that the numbers of claims follow the Poisson distribution with the weaker assumption that the numbers of claims have a variance proportional to the mean. The constant of proportionality is known as the dispersion parameter and it enables us to allow for heterogeneity; in the case of insurance data the dispersion parameter
also allows for the presence of duplicates in a portfolio. We use both the quasi-likelihood and the extended quasi-likelihood to estimate models for the smoothing and forecasting of mortality tables jointly with smooth estimates of the dispersion parameters. We present three main applications of our method: first, we show how taking account of dispersion reduces the volatility of a forecast of a mortality table; second, we smooth mortality data by amounts, ie, when deaths are amounts claimed and exposed-to-risk are sums assured; third, we present a joint model for mortality by lives and by amounts with the property that forecasts by lives and by amounts are consistent. Our methods are illustrated with data from the Continuous Mortality Investigation.

Original languageEnglish
Pages (from-to)33-52
Number of pages20
JournalAnnals of Actuarial Science
Volume5
Issue number1
DOIs
Publication statusPublished - 2011

Fingerprint

Mortality
Smoothing
Count
Dispersion Parameter
Quasi-likelihood
Forecast
Forecasting
Joint Model
Poisson distribution
Insurance
Volatility
Estimate
Tables
Table
Directly proportional
Modeling

Keywords

  • Amounts
  • Duplicates
  • Forecasting
  • Heterogeneity
  • Mortality
  • Over-dispersion
  • P-splines
  • Quasi-likelihood
  • Smoothing

Cite this

Currie, Iain David ; Djeundje Biatat, Viani. / Smoothing dispersed counts with applications to mortality data. In: Annals of Actuarial Science. 2011 ; Vol. 5, No. 1. pp. 33-52.
@article{0b35f4dbd8e14ed394340226f6730204,
title = "Smoothing dispersed counts with applications to mortality data",
abstract = "Mortality data are often classified by age at death and year of death. This classification results in a heterogeneous risk set and this can cause problems for the estimation and forecasting of mortality. In the modelling of such data, we replace the classical assumption that the numbers of claims follow the Poisson distribution with the weaker assumption that the numbers of claims have a variance proportional to the mean. The constant of proportionality is known as the dispersion parameter and it enables us to allow for heterogeneity; in the case of insurance data the dispersion parameter also allows for the presence of duplicates in a portfolio. We use both the quasi-likelihood and the extended quasi-likelihood to estimate models for the smoothing and forecasting of mortality tables jointly with smooth estimates of the dispersion parameters. We present three main applications of our method: first, we show how taking account of dispersion reduces the volatility of a forecast of a mortality table; second, we smooth mortality data by amounts, ie, when deaths are amounts claimed and exposed-to-risk are sums assured; third, we present a joint model for mortality by lives and by amounts with the property that forecasts by lives and by amounts are consistent. Our methods are illustrated with data from the Continuous Mortality Investigation.",
keywords = "Amounts , Duplicates, Forecasting, Heterogeneity, Mortality, Over-dispersion, P-splines, Quasi-likelihood, Smoothing",
author = "Currie, {Iain David} and {Djeundje Biatat}, Viani",
year = "2011",
doi = "10.1017/S1748499510000047",
language = "English",
volume = "5",
pages = "33--52",
journal = "Annals of Actuarial Science",
issn = "1748-4995",
publisher = "Cambridge University Press",
number = "1",

}

Smoothing dispersed counts with applications to mortality data. / Currie, Iain David; Djeundje Biatat, Viani.

In: Annals of Actuarial Science, Vol. 5, No. 1, 2011, p. 33-52.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Smoothing dispersed counts with applications to mortality data

AU - Currie, Iain David

AU - Djeundje Biatat, Viani

PY - 2011

Y1 - 2011

N2 - Mortality data are often classified by age at death and year of death. This classification results in a heterogeneous risk set and this can cause problems for the estimation and forecasting of mortality. In the modelling of such data, we replace the classical assumption that the numbers of claims follow the Poisson distribution with the weaker assumption that the numbers of claims have a variance proportional to the mean. The constant of proportionality is known as the dispersion parameter and it enables us to allow for heterogeneity; in the case of insurance data the dispersion parameter also allows for the presence of duplicates in a portfolio. We use both the quasi-likelihood and the extended quasi-likelihood to estimate models for the smoothing and forecasting of mortality tables jointly with smooth estimates of the dispersion parameters. We present three main applications of our method: first, we show how taking account of dispersion reduces the volatility of a forecast of a mortality table; second, we smooth mortality data by amounts, ie, when deaths are amounts claimed and exposed-to-risk are sums assured; third, we present a joint model for mortality by lives and by amounts with the property that forecasts by lives and by amounts are consistent. Our methods are illustrated with data from the Continuous Mortality Investigation.

AB - Mortality data are often classified by age at death and year of death. This classification results in a heterogeneous risk set and this can cause problems for the estimation and forecasting of mortality. In the modelling of such data, we replace the classical assumption that the numbers of claims follow the Poisson distribution with the weaker assumption that the numbers of claims have a variance proportional to the mean. The constant of proportionality is known as the dispersion parameter and it enables us to allow for heterogeneity; in the case of insurance data the dispersion parameter also allows for the presence of duplicates in a portfolio. We use both the quasi-likelihood and the extended quasi-likelihood to estimate models for the smoothing and forecasting of mortality tables jointly with smooth estimates of the dispersion parameters. We present three main applications of our method: first, we show how taking account of dispersion reduces the volatility of a forecast of a mortality table; second, we smooth mortality data by amounts, ie, when deaths are amounts claimed and exposed-to-risk are sums assured; third, we present a joint model for mortality by lives and by amounts with the property that forecasts by lives and by amounts are consistent. Our methods are illustrated with data from the Continuous Mortality Investigation.

KW - Amounts

KW - Duplicates

KW - Forecasting

KW - Heterogeneity

KW - Mortality

KW - Over-dispersion

KW - P-splines

KW - Quasi-likelihood

KW - Smoothing

U2 - 10.1017/S1748499510000047

DO - 10.1017/S1748499510000047

M3 - Article

VL - 5

SP - 33

EP - 52

JO - Annals of Actuarial Science

JF - Annals of Actuarial Science

SN - 1748-4995

IS - 1

ER -