City Research Online

Identifiability in Age/Period/Cohort Mortality Models

Hunt, A. & Blake, D. ORCID: 0000-0002-2453-2090 (2020). Identifiability in Age/Period/Cohort Mortality Models. Annals of Actuarial Science, 14(2), pp. 500-536. doi: 10.1017/s1748499520000123

Abstract

The addition of a set of cohort parameters to a mortality model can generate complex identifiability issues due to the collinearity between the dimensions of age, period and cohort. These issues can lead to robustness problems and difficulties making projections of future mortality rates. Since many modern mortality models incorporate cohort parameters, we believe that a comprehensive analysis of the identifiability issues in age/period/cohort mortality models is needed. In this paper, we discuss the origin of identifiability issues in general models before applying these insights to simple but commonly used mortality models. We then discuss how to project mortality models so that our forecasts of the future are independent of any arbitrary choices we make when fitting a model to data in order to identify the historical parameters.

Publication Type: Article
Additional Information: This article has been published in a revised form in Annals of Actuarial Science https://doi.org/10.1017/S1748499520000123. This version is free to view and download for private research and study only. Not for re-distribution or re-use. © copyright holder.
Publisher Keywords: Mortality modelling, age/period/cohort models, identification issues, projection
Subjects: G Geography. Anthropology. Recreation > GF Human ecology. Anthropogeography
H Social Sciences > HB Economic Theory
H Social Sciences > HF Commerce > HF5601 Accounting
Departments: Bayes Business School > Finance
SWORD Depositor:
[thumbnail of wp1509.pdf]
Preview
Text - Accepted Version
Download (455kB) | Preview

Export

Add to AnyAdd to TwitterAdd to FacebookAdd to LinkedinAdd to PinterestAdd to Email

Downloads

Downloads per month over past year

View more statistics

Actions (login required)

Admin Login Admin Login