ARIMA模型预测甲肝发病

ARIMA Model on Prediction of Hepatitis A Attack

目的探讨ARIMA模型在甲肝预测方面的应用,建立甲肝发病预测模型,并证明模型的适用性。方法利用甘肃省1990-01/2007-12甲肝发病数资料,通过SPSS Expert Modeler拟合ARIMA模型,用Q统计量法对模型适应性进行检验。结果建立ARIMA(0,1,1)(0,1,1)模型,模型统计量Q=20.637,P>0.05,证实了该模型的适用性。结论ARIMA模型可用于甲肝发病的动态分析和短期预测。

Objective To explore the application of auto regressive integrated moving average （ARIMA） and establish a predictive model for Hepatitis A and, to prove the applicability of the model. Methods Samples which caught Hepatitis A from 1990 Jan to 2007 Dec in Gansu Province were subjected. SPSS Expert Modeler was used to fit ARIMA model, and Q statistic was used to verify the applicability of the model. Results The model of ARIMA （0, 1, 1 ） （0, 1, 1 ） was established. The statistic of Q was 20. 637, which verified the applicability of this model. Conclusion The ARIMA model can be used to analyze the Hepatitis A attack and make a short term prediction.