摘要
在医疗费用的预测中,通常假设门诊费用与住院费用相互独立,事实上它们之间往往存在一定的相依关系。它们的相依性可以通过Copula函数来描述。在已知医疗费用发生的条件下,假设门诊费用和住院费用分别服从伽玛分布、逆高斯分布、对数正态分布和GB2分布,可以建立门诊费用与住院费用相互依赖的Copula回归模型。本文将此模型应用于一组实际的医疗费用数据,结果表明,考虑相依关系的回归模型要优于独立假设下的医疗费用预测模型。
It is usually assumed that expenditures for outpatient visits and inpatient visits are independent,but the fact is that they are dependent to some extent.Their dependence may be captured by Copula functions.Under the assumption that the expenditures for outpatient visits and inpatient visits follow gamma distribution,inverse-Gaussian distribution,log-normal distribution and GB2 distribution,respectively,the corresponding copula regression models are established.The model is applied to a real data set of medical expenditures and the result shows that the Copula-based regression model is superior to independent regression models.
出处
《数理统计与管理》
CSSCI
北大核心
2015年第5期761-768,共8页
Journal of Applied Statistics and Management
基金
教育部重点研究基地重大项目(12JJD790025)
