City Research Online

Abstract

This thesis investigates the use of parametric models for projecting mortality rates. The basic framework used is that of generalised linear models and can be considered as an extension of the Gompertz-Makeham models (Forfar, McCutcheon and Wilkie, 1988) to include calendar period. The data considered are the CMI ultimate experience for immediate annuitants (male and female) over the period 1946 to 1994 and for life office pensioners (male and female) over the period 1983 to 1996.

The modelling structure suggested by Renshaw, Haberman and Hatzopoulos (1996) is used to investigate the data sets and to determine a range of suitable models, analysing the data by age and calendar period. The properties of these models are investigated and recommendations are made on which models are appropriate for use in projections.

Mortality improvement models are derived from the recommended models and the associated reduction factors are compared with CMI mortality reduction factors.

In addition, the female annuitants’ ultimate experience is investigated using a method that combines parametric and time series models to generate forecasts. The procedure used by McNown and Rogers (1989) is used to project forces of mortality over time. The parametric models (Gompertz-Makeham type) are fitted in the framework of generalised linear models. Projected forces of mortality based on the combined parametric-time series model are compared with the projected forces of mortality recommended on the basis of the parametric models.

Publication Type:	Thesis (Doctoral)
Subjects:	H Social Sciences > HA Statistics
Departments:	Bayes Business School > Actuarial Science & Insurance > Statistical Research Reports Bayes Business School > Bayes Business School Doctoral Theses Doctoral Theses

Export

Downloads