ARIMA乘积季节模型在青州市布鲁氏菌病发病预测中的应用

Application of multiple seasonal ARIMA model in forecasting the incidence of brucellosis in Qingzhou

目的应用自回归求和移动平均(ARIMA)乘积季节模型预测青州市布鲁氏菌病月发病数,构建青州市布鲁氏菌病月发病数的预测模型,为青州市布鲁氏菌病防控措施提供科学依据。方法收集青州市2011—2017年布鲁氏菌病监测数据,采用SPSS 25.0统计软件建立ARIMA时间序列模型,并对模型进行检验,预测出2018年的布鲁氏菌病月发病数,用2018年布鲁氏菌病实际月发病数评价模型的预测效果。结果模型ARIMA(0,1,1)(1,1,0)12标准化的BIC值最小,Box-Ljung检验统计量Q=23.746,P>0.05,残差序列为白噪声,确定为最优模型。结论ARIMA乘积季节模型短期预测青州市布鲁氏菌病月发病数效果较好。

Objective To predict the monthly incidence of brucellosis in Qingzhou by multiple seasonal ARIMA model of autoregressive integrated moving average(ARIMA),and to construct a prediction model for the monthly incidence of brucellosis in Qingzhou so as to provide scientific basis for prevention and control measures of brucellosis in Qingzhou.Methods The monitoring data of brucellosis in Qingzhou from 2011 to 2017 were collected,ARIMA time series model was established with SPSS 25.0 statistical software,the model was tested to predict the monthly incidence of brucellosis in 2018,and the prediction effect of the model was evaluated by the actual monthly incidence of brucellosis in 2018.Results The normalized BIC value of ARIMA(0,1,1)(1,1,0)12 model is the smallest,the Box-Ljung test statistic is as follows:Q=23.746,P>0.05,the residual sequence is white noise,thus it is determined to be the optimal model.Conclusion Multiple seasonal ARIMA model is effective in short-term prediction of monthly incidence of brucellosis in Qingzhou.