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.

The comparative mortality of an elite group in the long run of history: an observational analysis of politicians from 11 countries

“…To quantify changes in absolute inequalities between politicians and the general population, we estimated gaps in their respective remaining life expectancies from the age of 45 years (mean age of entry into parliament). For politicians, we fitted Gompertz parametric proportional hazards models [31] using age as time scale to data in consecutive 10-year time windows. These models were used to estimate the remaining life expectancy of a politician in each time window, which was then compared with the remaining life expectancy of the general population in the same time window.…”

A semiparametric Gumbel regression model for analyzing longitudinal data with non‐normal tails

“…7 Basellini et al applied Gumbel distributions to achieve reparametrization of mortality models used in demographic data. 8 Under the Bayesian framework, Roy and Dey studied the property of posterior distributions arising in categorical and survival regression models under the generalized extreme value distribution. 9 Ghosh developed a Bayesian hierarchical regression model for extreme precipitation events.…”