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

Abstract

This study aims to model Lee-Carter mortality with a Bayesian approach, where the parameters in the model are assumed to be random variables. The data used in this study is data on mortality rates by age group from the period 1950–2015. The sourced of data was from the UN website. Age groups are categorized by age 0 years, 1-5 years, 6-10 years, 11-15 years, ..., 86-90 years. The results of this study are from Bayes estimation obtained information that the average infant mortality rate (population aged less than one year) is high, then at the age of toddlers (1-4 years) average mortality rate decreases. Furthermore, the average mortality rate for children, adolescents, young and older people has increased again. Meanwhile, the relative speed of the pattern of changes in mortality at infant age (less than one year) is high enough. At the age of toddlers (1 – 4 years), the pattern of changes in mortality has increased. Then, in the population of the next age group until the older age group, the mortality continues to decrease. The pattern of changes in mortality is lowest in the elderly population.

Labor Force Participation Rate and Expected Length of Retirement 2001-2047: A Case Study in Malaysia

“…Several research suggested tweaks to the Lee-Carter model that would make it more effective at modeling and forecasting rates. Some examples of these adjustments are using a Bayesian method [30] incorporating randomness or an error term into the model [30], [31], or employing a state-space model to get around the biodemographic constraint and using resampling method to improve forecasting accuracy [32]. Moreover, Lee-Carter model has been contrasted with other models, including the neural networks [33], autoregressive integrated moving average (ARIMA) model [34], and modified Lee-Carter model with bias-corrected estimators [35].…”

Labor Force Participation Rate and Expected Length of Retirement 1989-2066: Comparison of Several OECD Countries

“…Several research suggested tweaks to the Lee-Carter model that would make it more effective at modeling and forecasting rates. Some examples of these adjustments are using a Bayesian method [26] incorporating randomness or an error term into the model [26,27], or employing a state-space model to get around the biodemographic constraint. Moreover, Lee-Carter model has been contrasted with other models, including the neural networks ( [28]), autoregressive integrated moving average (ARIMA) model ( [29]), and modified Lee-Carter model with bias-corrected estimators ( [30]).…”