The Three-Way Lee-Carter approach: Forecasting Malaysian sub-population mortality rates by states

Abstract

This research aims to predict the mortality rates of Malaysian sub-populations in thirteen different states using the Three-Way Lee-Carter model: the extended version of the Lee-Carter model. This model considers the coherence characteristic between subpopulations as it allows combination estimates of the three variables: i) time, ii) age and iii) different subpopulations, which is useful to assess the magnitude of mortality differential between subpopulations. The Three-Way Lee-Carter model has never been tested using Malaysian mortality rates, particularly to forecast mortality of subpopulations in different states. Hence this research predicts the thirteen-state populations' mortality rates and compares the model's performance to the original Lee-Carter model. The collected data includes mortality rates by age, gender, and states obtained from the Department of Statistics Malaysia from 1991 until 2018. Results show that the Three-Way Lee-Carter model successfully fits into the Malaysia data better than the original Lee-Carter model. In terms of out-sample forecasts, the Three-Way Lee-Carter model outperforms the Lee-Carter model for eight subpopulations including for Kelantan males, Perlis males, Sabah males, Terengganu males, Perak females, Perlis females, Sarawak females and Selangor females.