ARIMA乘积季节模型在盐城市手足口病疫情预测中的应用

目的 探讨自回归移动平均（autoregressive integrated moving average model，ARIMA）乘积季节模型在盐城市手足口病发病趋势预测的可行性。方法 利用盐城市2009年1月至2015年12月的手足口病月发病率建立ARIMA乘积季节模型，并对2016年手足口病发病趋势进行预测。结果 盐城市手足口病预测模型为ARIMA（1，0，1）（1，1，0）12，该模型的参数估计具有统计学意义，拟合优度检验统计量最小Normalized BIC=2.997，残差序列检验统计量Ljung-Box=20.692（P0.05），残差为白噪声，模型能够拟合出手足口病的发病趋势，且实际值都在95%可信区间内，但模型拟合的平均误差率为41.296%，检验模型预测效果的平均误差率为23.998%，模型预测精度高于拟合精度。结论 运用ARIMA乘积季节模型能够对盐城市手足口病发病趋势进行预测和动态分析，对手足口病预防控制产生积极的指导作用。

Application of ARIMA product seasonal model in predicting incidence of hand foot and mouth disease in Yancheng

Objective To explore the feasibility of multiple seasonal autoregressive integrated moving average (ARIMA) product seasonal model in predicting the incidence of hand, foot and mouth disease (HFMD) in Yancheng. Methods The ARIMA product seasonal model was established based on monthly incidence rates of HFMD in Yancheng from January 2009 to December 2015. Results Through the tests of parameters and goodness of fit as well as white-noise residuals, we finalized the model ARIMA(1, 0, 1)(1, 1, 0)12, of which the normalized BIC was 2.997, Ljung-Box was 20.692(P0.05), the model could fit the incidence trend over the period, the values were in 95% confidence interval and the mean error rate was 41.296%. The mean error rate of another checking model was 23.998%. The prediction accuracy was better than fitting accuracy. Conclusion The model can be used to predict the incidence trend of HFMD in Yancheng, which might play a positive role in the prevention and control of HFMD.