{"title":"Forecasting Indonesia mortality rate using beta autoregressive moving average model","authors":"","doi":"10.28919/cmbn/8184","DOIUrl":null,"url":null,"abstract":": The mortality rate serves as one measure of the health sector as well as a tool for identifying populations that should receive specific health and development programs. The mortality rate can be used to determine a nation's level of welfare and standard of living. The mortality rate also affects the pricing of insurance premiums, the calculation of the benefit reserve for annuity products, actuarial risk management, and pension plans. A model is required to predict the mortality rate in the future because it is a random variable that varies over time and is in the range of (0,1). The Beta Autoregressive Moving Average (βARMA) model is a development of Beta regression and can be used to model and forecast mortality rates. Based on data on Indonesia's annual death rates from 1960 to 2020, we constructed a βARMA model for forecasting Indonesia's mortality rate. The best βARMA model was selected using Akaike's Information Criterion (AIC) value, and forecasting accuracy was assessed using Root Mean Square Error (RMSE). For Indonesia's annual mortality rate data, the best βARMA model produces an RMSE value of 0.0001.","PeriodicalId":44079,"journal":{"name":"Communications in Mathematical Biology and Neuroscience","volume":null,"pages":null},"PeriodicalIF":0.5000,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Communications in Mathematical Biology and Neuroscience","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.28919/cmbn/8184","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"COMPUTER SCIENCE, INFORMATION SYSTEMS","Score":null,"Total":0}
引用次数: 0
Abstract
: The mortality rate serves as one measure of the health sector as well as a tool for identifying populations that should receive specific health and development programs. The mortality rate can be used to determine a nation's level of welfare and standard of living. The mortality rate also affects the pricing of insurance premiums, the calculation of the benefit reserve for annuity products, actuarial risk management, and pension plans. A model is required to predict the mortality rate in the future because it is a random variable that varies over time and is in the range of (0,1). The Beta Autoregressive Moving Average (βARMA) model is a development of Beta regression and can be used to model and forecast mortality rates. Based on data on Indonesia's annual death rates from 1960 to 2020, we constructed a βARMA model for forecasting Indonesia's mortality rate. The best βARMA model was selected using Akaike's Information Criterion (AIC) value, and forecasting accuracy was assessed using Root Mean Square Error (RMSE). For Indonesia's annual mortality rate data, the best βARMA model produces an RMSE value of 0.0001.
期刊介绍:
Communications in Mathematical Biology and Neuroscience (CMBN) is a peer-reviewed open access international journal, which is aimed to provide a publication forum for important research in all aspects of mathematical biology and neuroscience. This journal will accept high quality articles containing original research results and survey articles of exceptional merit.