基于时间序列马尔可夫模型的我国城镇职工基本医疗保险基金收支平衡预测研究

Prediction of Income and Expenditure Balance of Basic Medical Insurance Fund for Urban Employees in China Based on Time Series Markov Model

目的:利用1995—2015年间全国城镇职工基本医疗保险基金收入和支出总额的时间序列,预测未来10年基金的收支平衡情况。方法:利用ARIMA模型构建基金收入支出总额的一次拟合模型,再利用马尔可夫模型来修正拟合值构建二次模型,从而提高预测的精度。结果:基金收入一次模型的平均相对误差为5.81%,二次模型降低为2.01%;基金支出一次模型的平均相对误差为9.14%,二次模型降低为5.35%。结论:从全国情况来看,城镇职工基本医疗保险保持现有的收入支出政策不变,在2016年到2025年不会出现年度超支。建议医保管理部门加强顶层设计,整合统筹基金和个人账户基金,提高基金统筹层次,增强医保基金的抗风险能力。

Objective： To predict the balance of payments in the next 10 years by using the time series of the total income and ex- penditure of the basic medical insurance fund for urban employees from 1995 to 2015. Methods： A fitting model of construction fund total amount paid by the ARIMA model, to correct the fitted value of constructing two models based on Markov model, so as to im- prove the prediction accuracy. Results： The average relative error of the primary income model was 5.81%, and the quadratic model was 2.01%. The average relative error of the fund expenditure model was 9.14%, and the quadratic model was 5.35%. Conclusion： From the national situation, the basic medical insurance policy for urban employees remains unchanged, and there will be no annual overruns from 2016 to 2025. It suggested that the medical insurance administration department should enhance the top-layer design, integrate the pooling fund and individual account fund, improve the overall polling hierarchy and strengthen the medical insurance fund＇s capacity to resist the risks.