乌鲁木齐市2005-2017年甲肝发病时间序列分析  

Time series analysis of hepatitis A incidence in Urumqi from 2005 to 2017

作　　者：李新凤[1] 刘霞[1] 高枫[1] 王培生[1] 陈保林[1] LI Xinfeng;LIU Xia;GAO Feng;WANG Peisheng;CHEN Baolin(Urumqi Center for Disease Control and Prevention,Xinjiang 830026,China)

机构地区：[1]乌鲁木齐市疾病预防控制中心

出　　处：《医学动物防制》2019年第11期1112-1114,共3页Journal of Medical Pest Control

基　　金：乌鲁木齐市卫生计生委科技计划项目(201828)

摘　　要：目的通过时间序列分析了解乌鲁木齐市甲肝发病规律,建立时间序列模型用于预测甲肝发病。方法收集2005-2017年甲肝报告发病数据,使用SPSS 21.0软件进行时间序列拟合,选择拟合效果指标最好的模型用于预测。结果①按病例数进行拟合,乌鲁木齐市甲肝发病符合简单季节模型(R2=0.634,ljung-box Q(18)检验统计量25.668,P=0.029)。每年10~11月均有一次发病高峰出现。②按发病率进行拟合,乌鲁木齐市甲肝发病符合winter乘法模型(R2=0.800,ljung-box Q(18)检验统计量25.617,P=0.036)。③按发病率预测的数据与实测数据进行对比发现,预测数据与实测数据差异无统计学意义(T=2.376,P=0.076)。结论本次研究建立了乌鲁木齐市甲肝发病的模型,为后期的人员培训、物资准备做参考,同时对甲肝的预防控制有一定的指导作用。Objective To understand the incidence of hepatitis A in Urumqi by time series analysis and establish a time series model to predict the incidence of hepatitis A.Methods Data of reported hepatitis A cases from 2005 to 2017 were collected and time series fitting was performed by SPSS 21.0 software.The best fitting model was selected for prediction.Results①According to the number of cases,the incidence of hepatitis A in Urumqi conformed to the simple seasonal model(R2=0.634,ljung-box Q(18)test statistic 25.668,P=0.029).It can be seen from the chart that there is a peak of disease every November.②The incidence of hepatitis A in Urumqi was fitted by Winter multiplication model(R2=0.800,ljung-box Q(18)test statistic25.617,P=0.036).③By comparing the predicted data with the measured data,there was no significant difference between the predicted and measured data(T=2.376,P=0.076).Conclusion This study established a model of hepatitis A in Urumqi,which can be used to predict the incidence of hepatitis A in the future work of disease prevention and control.It will play a guiding role in the prevention and control of hepatitis A.

关 键 词：甲肝 发病率 时间序列 预测 

分 类 号：R512.61[医药卫生—内科学]