Modeling and Forecasting Norway Mortality Rates using the Lee Carter Model

Abstract

Mortality data is an important element in the fields of actuarial science, health, epidemiology and national planning. Mortality levels are generally regarded as indicators of a general welfare of a national population and its subgroups. It reflects the quality of life within quantity. Therefore, developing a model for forecasting mortality rate will help a nation to develop its quality of life. The Lee and Carter stochastic mortality model has been used for fitting and forecasting the mortality rate of Norway which is considered as the country with the highest living standards based on the human development index. The data set contains Norway mortality data from 1946-2014. The Singular Value Decomposition (SVD) approach is used for estimating the parameters of Lee Carter model. Auto Regressive Integrated Moving Average (ARIMA) time series model is used for forecasting the mortality values. In this study 97.5 % variance of Norway mortality data could be explained by the proposed Lee Carter model. The best fitting ARIMA model for Norway data is identified as ARIMA (3,2,1) with drift. The predicted Lee Carter model gives a good fit to Norway data over a wide range of ages but shows poor performance below age 4 years and after age 55 years. Therefore, improvements in the Lee Carter model is needed to obtain better predictions for the ages below 4 years and after 55 years. This proposed model can be used to construct the life tables, pension scheme planning and actuarial science applications. Keywords:

Lee-Carter Modeling for Mortality in Indonesia With a Bayesian Approach

“…Lee-Carter introduced a method for modeling and predicting mortality (in this case was ASDR) with a stochastic approach (then this method is known as the Lee-Carter model [2]. The Lee-Carter model has been successfully applied to mortality forecasting in several countries, including Norway [3], Malaysia [4], Indonesia [5] [6], the US [2], Nordic (Denmark, Finland, Norway, and Sweden) [7], Sweden [8], Peru [9], India [10], Hungary [11], Sri Lanka [12] and Mauritius [13]. Several studies that have already been mentioned previously refer to the frequency approach in the parameter estimation process.…”