Lee-Carter模型在死亡率预测中的应用.pdf

Statistical and Application 统计学与应用, 2015, 4(3), 155-161 Published Online September 2015 in Hans. /journal/sa /10.12677/sa.2015.43017 Application of Lee-Carter Model in Predicting Mortality Qiuyun Zhang School of Mathematics and Information Sciences, Guangzhou University, Guangzhou Guangdong Email:163.com th th th Received: Aug. 17 , 2015; accepted: Sep. 5 , 2015; published: Sep. 8 , 2015 Copyright © 2015 by author and Hans Publishers Inc. This work is licensed under the Creative Commons Attribution International License (CC BY). /licenses/by/4.0/ Abstract Changes in mortality rates have an impact on the social security system, which is a time-varying dynamic random variable. Basic pension insurance payment shall comply with the dynamic changes of population mortality. In this paper, using Lee-Carter model [1] forecasts the future mortality trends of population, the prediction of time factor κt in the future, the paper uses gene- ralized difference model for prediction. And compared with the ARIMA model, the result of gene- ralized difference model was better. Keywords Mortality Prediction, Lee-Carter Model, ARIMA Model, The Generalized Difference Model Lee-Carter模型在死亡率预测中的应用 张秋芸 广州大学数学与信息科学学院，广东 广州 Email:163.com 收稿日期：2015年8月17 日；录用日期：2015年9月5 日；发布日期：2015年9月8 日 摘 要 人口死亡率变化对社会保障系统有一定影响，它是时变的动态随机变量。基本养老保险的给付须遵从人 文章引用: 张秋芸 (2015) Lee-Carter 模型在死亡率预测中的应用. 统计学与应用, 3, 155-161. /10.12677/sa.2015.43017 张秋芸 口动态死亡率变化规律。本文利用Lee-Carter [1]模型对未来人口死亡率变动趋势进行预测。对未来时间 因子κ的预测时，用广义差分模型预测。并与ARIMA模型比较，结果广义差分模型预测效果较好。 t 关键词 死亡率预测，Lee-Carter模型，ARIMA模型，广义差分模型 1. 引言