Volume 32 - Article 36 | Pages 1031-1048
The Gompertz force of mortality in terms of the modal age at death
|Date received:||22 Jul 2014|
|Date published:||20 May 2015|
|Keywords:||Gompertz force of mortality, Gumbel distribution, maximum-likelihood estimation, modal age at death, parameter correlation|
|Weblink:||All publications in the ongoing Special Collection 8 "Formal Relationships" can be found at http://www.demographic-research.org/special/8/|
Background: The Gompertz force of mortality (hazard function) is usually expressed in terms of a, the initial level of mortality, and b, the rate at which mortality increases with age.
Objective: We express the Gompertz force of mortality in terms of b and the old-age modal age at death M, and present similar relationships for other widely-used mortality models. Our objective is to explain the advantages of using the parameterization in terms of M.
Methods: Using relationships among life table functions at the modal age at death, we express the Gompertz force of mortality as a function of the old-age mode. We estimate the correlation between the estimators of old (a and b) and new (M and b) parameters from simulated data.
Results: When the Gompertz parameters are statistically estimated from simulated data, the correlation between estimated values of b and M is much less than the correlation between estimated values of a and b. For the populations in the Human Mortality Database, there is a negative association between a and b and a positive association between M and b.
Conclusions: Using M, the old-age mode, instead of a, the level of mortality at the starting age, has two major advantages. First, statistical estimation is facilitated by the lower correlation between the estimators of model parameters. Second, estimated values of M are more easily comprehended and interpreted than estimated values of a.
Trifon I. Missov - Max-Planck-Institut für Demografische Forschung, Germany
Adam Lenart - Max Planck Odense Center on the Biodemography of Aging, Denmark
Laszlo Nemeth - Max-Planck-Institut für Demografische Forschung, Germany
Vladimir Canudas-Romo - Syddansk Universitet, Denmark
James W. Vaupel - Max-Planck-Institut für Demografische Forschung, Germany
Other articles by the same author/authors in Demographic Research
Similar articles in Demographic Research