ARIMA乘积季节模型在我国甲肝发病预测中的应用

Application of multiple seasonal ARIMA model in forecasting the incidence of hepatitis A in China

目的：应用求和自回归移动平均模型（ARIMA）乘积季节模型对我国病毒性甲型肝炎进行预测分析,为甲型肝炎的防治提供决策依据。方法：对1994~2012年我国甲型肝炎月发病数的历史疫情数据建立ARIMA乘积季节模型,应用Eviews 6.0软件进行模型拟合,对2013年上半年甲型肝炎的月发病数进行预测,并用实际数据评估模型预测效果。结果：ARIMA（1,1,0）（2,1,2）12模型较好地拟合了既往甲肝的实际发病序列,也获得了较好的预测效果。结论：ARIMA模型能够较好地模拟我国甲型肝炎的发病趋势,预测效果良好,可为甲肝疫情的防控提供一定的科学数据。

Objective：To forecast the incidence of hepatitis A in China by multiple seasonal autoregressive integrated moving average（ARIMA） model,and to provide decision basis for prevention and control of hepatitis A. Methods：ARIMA model was established according to the data of monthly reported hepatitis A cases in China from Jan.1994 to Dec.2012. Eviews 6.0 software was performed to construct the ARIMA model,and the constructed model was applied to predict monthly incidence in the first half of 2013. The model was evaluated by actual data. Results：ARIMA（1,1,0）（2,1,2）12 exactly fitted the incidence of the previous time series,and got a good result on the predictive incidence in 2013. Conclusion：The multiple seasonal ARIMA model can be performed to make a short-term prediction and a dynamic analysis on the incidence of hepatitis A in China,and can provide a scientific basis for the prevention and control of hepatitis A.