论文部分内容阅读
目的探讨SARIMA模型用于新疆乙肝月发病率预测的可行性,为制定防控策略提供科学参考。方法采用带有季节性的自回归移动平均模型(SARIMA),分析将其用于新疆乙肝发病率预测的可行性,对模型进行参数估计及残差检验,根据AIC及BIC准则确定最适合的SARIMA模型,讨论该模型的拟合及预测效果。结果 SARIMA(1,1,2)(0,1,0)12模型很好地拟合了新疆乙肝月发病率变化规律,模型预测值与实际值间的相对误差及均方误差较小。结论SARIMA(1,1,2)(0,1,0)12模型能够较好地用于新疆乙肝月发病率预测,可为新疆的乙肝防控提供科学参考。
Objective To explore the feasibility of using SARIMA model to predict monthly incidence of hepatitis B in Xinjiang and to provide scientific reference for making prevention and control strategies. Methods The seasonal autoregressive moving average model (SARIMA) was used to analyze the feasibility of using it to predict the incidence of hepatitis B in Xinjiang. The model was estimated and the residuals were tested. According to AIC and BIC criteria, the most suitable SARIMA Model to discuss the model fitting and forecasting effect. Results The SARIMA (1,1,2) (0,1,0) 12 model fitted well the monthly incidence of hepatitis B in Xinjiang. The relative error and the mean square error between predicted and actual values of the model were small. Conclusion The SARIMA (1,1,2) (0,1,0) 12 model can be used to predict the monthly incidence of hepatitis B in Xinjiang and provide a scientific reference for the prevention and control of hepatitis B in Xinjiang.