基于均衡关系的中国人口死亡率预测模型

发布时间：2018-04-20 08:44

本文选题：死亡率预测 + Lee-Carter模型　；参考：《统计与信息论坛》2016年10期

【摘要】：人口死亡率反映了人口的死亡程度,准确预测死亡率是人口科学及人口经济学研究的重点之一,同时也是长寿风险测量的重要数据基础。基于Lee-Carter模型,探索中国大陆与台湾地区死亡率的相关性,通过协整分析考虑两地死亡率的长期均衡关系,创新性地建立基于相关性的向量误差修正模型(VECM),克服传统自回归移动平均模型(ARIMA)使用有限数据进行预测的局限性;均方预测误差作为检验标准,结果表明:基于VECM模型的预测效果比传统的预测效果更佳;基于中国大陆地区和台湾地区的死亡率长期均衡关系,可以为两地联合长寿债券的定价提供重要参考。
[Abstract]:The death rate of population reflects the degree of death of the population. It is one of the key points in population science and population economics to predict the death rate accurately, and it is also an important data base for the risk measurement of longevity. Based on the Lee-Carter model, this paper explores the correlation between the mortality rate in mainland China and Taiwan, and considers the long-term equilibrium relationship between the two mortality rates through cointegration analysis. A vector error correction model based on correlation is established to overcome the limitation of the traditional autoregressive moving average model (ARIMA) which uses finite data to predict, and the mean square prediction error is used as the test standard. The results show that the prediction effect based on the VECM model is better than that of the traditional one, and the long-term equilibrium of mortality in China and Taiwan can provide an important reference for the pricing of the joint longevity bond between China and Taiwan.
【作者单位】：暨南大学经济学院;
【基金】：国家自然科学基金面上项目《带Levy跳的多因子市道轮换框架下的仿射利率结构研究》(71471075) 教育部人文社会科学研究一般项目《基于市道轮换框架下带Levy跳的高频数据的波动率研究》(14YJAZH052) 中央高校基本科研业务费专项资金资助项目(暨南跨越计划)《PMCMC算法在市道轮换框架下利率结构模型中的应用》(15JNKY003)
【分类号】：C924.25

【相似文献】