季节性ARIMA模型在广州市手足口病疫情预测中的应用

Application of seasonal ARIMA model on the prediction of incidence of hand foot and mouth disease in Guangzhou

目的探讨应用季节性ARIMA模型预测广州市手足口病发病情况的可行性。方法利用＂传染病报告信息管理系统＂数据,应用SPSS 13.0统计软件对广州市2009年1月至2014年6月手足口病发病数建立季节性ARIMA模型,使用所建模型对2014年7~12月发病情况进行预测。结果广州市手足口病发病特征以年为流行周期,每年有2个发病高峰;应用季节性ARIMA方法进行模型识别与估计后,建立ARIMA（1,0,1）（2,1,0）12模型,预测平均相对误差为0.22,预测效果较好。结论季节性ARIMA模型能较好的拟合广州市手足口病发病序列并进行短期的有效预测。

Objective To assess the feasibility of using the seasonal autoregressive integrated moving average （ARIMA） model in predicting the incidence of hand foot and mouth disease （HFMD） in Guangzhou. Meth- ods The seasonal ARIMA model was created based on the monthly ease numbers of HFMD collected from the national disease reporting information system in Guangzhou city from January 2009 to June 2014 by using SPSS 13.0 software. The model was then used to predict the incidence of HFMD during July to December 2014. Results There were two incidence peaks of HFMD every year in Guangzhou, and the model of ARIMA （1, 0, 1） （2, 1, 0）12 fit the time series well with, and the mean error of 0.22. Conclusions The seasonal ARIMA model can better fit the incidence of HFMD in Guangzhou, and can be used for disease prediction in the short-term.