ARIMA模型在盐城市肺结核发病率预测中的应用

Application of ARIMA model in predicting incidence of pulmonary tuberculosis incidence in Yancheng City

目的:探讨差分自回归移动平均(autoregressive integrated moving average,ARIMA)模型在盐城肺结核发病率预测中的应用。方法:利用盐城市2011年1月—2016年12月的肺结核月发病率建立乘积季节ARIMA模型,并评价模型的预测效能。结果:盐城市肺结核预测模型为ARIMA(1,1,0)(2,1,0)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标准化贝叶斯信息准则(Normalized BIC)=-0.144,残差序列检验统计量Ljung-Box=0.247(P>0.05),残差为白噪声,模型能够拟合出肺结核的发病趋势。结论:ARIMA模型可以应用于盐城市肺结核发病趋势的预测,对肺结核的预防控制有积极的意义。

Objective： To explore the feasibility of multiple seasonal autoregressive integrated moving average（ARIMA） model to forecast the epidemic trends of pulmonary tuberculosis incidence. Methods： The ARIMA model was established based on monthly incidence rates of pulmonary tuberculosis in Yancheng City, from Jan 2011 to Dec 2016,and evaluate the model predictive performance. Results： Through the test of parameters and goodness of fit as well as white-noise residuals, we finalized the model ARIMA（1,1,0）（2,1,0）,2, of which Normalized BIC=-0.144, Ljung-Box=0.247（P〉0.05）, the model can fit the incidence trend over the period. Conclusions： The model can predict the incidence trend of pulmonary tuberculosis, and it plays a positive role in preventing and controlling pulmonary tuberculosis.