基于半参数分位数回归模型的老年人医疗费用影响因素研究  

Study on the Influencing Factors of the Medical Expenses of the Elderly Using the Semi-parametric Quantile Regression Model

作　　者：李呈呈 刘红慧 陈曦来 庄梦 刘恋 涂新华 徐城伟 段禹 王静[1,2] Li Chengcheng;Liu Honghui;Chen Xilai(Department of Epidemiolagy and Health Statistics,Anhui Medical University 230032,Hefei)

机构地区：[1]安徽医科大学公共卫生学院流行病与卫生统计学系,230032 [2]安徽医科大学公共卫生学院医学数据处理中心 [3]安徽财经大学统计与应用数学学院 [4]中国科学技术大学附属第一医院安徽省立医院

出　　处：《中国卫生统计》2022年第4期513-517,共5页Chinese Journal of Health Statistics

基　　金：全国医学专业学位研究生教育指导委员会立项资助(B2-YX20190203-01);安徽省教育厅自然科学研究重点项目(KJ2017A164);国家青年基金项目(11801010)。

摘　　要：目的将半参数分位数回归模型应用于老年人医疗费用的研究,探究不同医疗支出水平对其影响因素的响应情况并提出建议,为实现健康老龄化提供参考依据。方法使用中国健康与养老追踪调查(CHARLS)2018年数据库,使用R 4.0.4软件建立半参数分位数回归模型探究老年人医疗费用的影响因素。结果年龄、个人年收入、性别、居住地城乡分布、自评健康状况及医疗保险是影响老年人医疗费用的重要因素。年龄增加使老年人医疗支出增加,尤其在低医疗支出的高龄老年人中,年龄增加的效应迅速变强;个人收入对老年人医疗支出的影响效应呈现U型,即对低收入与高收入的老年人医疗支出影响较高,而对中等收入老人影响较低;不同性别老年人医疗支出差异较小,女性总体略高于男性;城市老年人医疗支出显著高于农村老年人,且这种差异在低医疗支出和高医疗支出老年人群中更为明显;自评健康状况和参加医疗保险情况也是影响老年人医疗支出的重要因素。结论半参数分位数回归模型在对老年人医疗支出影响因素的研究有较好的效果。不同医疗支出水平对于影响因素有着不同的响应情况。Objective To apply the semi-parametric quantile regression model to the study of the medical expenses of the elderly.To explore the response of different medical expenditure levels to its influencing factors and put forward suggestions to provide a reference basis for the healthy aging in China.Methods Using the China Health and Retirement Longitudinal Study(CHARLS)2018 database,R 4.0.4 was used to establish a semi-parametric quantile regression model to explore the influencing factors of medical costs in the elderly.Results The results showed that age,personal income,gender,urban and rural distribution of residence,self-rated health status and health insurance were important factors of the medical expenses of the elderly.The increase of age was an important factor,especially in the older elderly with low medical expenditure.Individual income had a U-shaped influence,which meant a higher influence on the medical expenditure of the elderly with low and high income,but a lower influence on the elderly with middle income.There was little difference in medical expenditure among the elderly of different genders,and female was slightly higher than male in general.The medical expenditure of the urban elderly was significantly higher than that of the rural elderly,and this difference was more obvious in the elderly with low medical expenditure and high medical expenditure.The self-rated health status and the health insurance were also important factors.Conclusion Semi-parameter quantile regression model has a good effect on the study of the factors affecting the medical expenditure of the elderly.Different levels of medical expenditure has different responses to the influencing factors.

关 键 词：分位数回归 半参数分位数模型 老年人 老龄化 医疗支出 

分 类 号：R195.1[医药卫生—卫生统计学]