论文部分内容阅读
目的利用时间序列分析方法动态研究手足口病发病趋势,探讨合理的预测模型,为宝鸡市制定手足口病的预防控制措施提供决策依据。方法应用时间序列分析方法对宝鸡市2008 2014年手足口病月发病数据进行分析并建立预测模型,对建立的预测模型进行参数估计、模型诊断、模型评价,选择最优预测模型,利用所得到的模型对2015年1 6月的发病情况进行预测,并评价其预测效果。结果通过参数和模型拟合优度检验以及残差白噪声序列检验,得到模型ARIMA(1,1,1)(0,1,1)12,R2=0.820,标准化的BIC=10.507,Ljung-Box=4.631(P=0.995),2015年1 6月手足口病月发病数预测值和实际值的平均相对误差仅为2.34%,实际值都在95%可信区间内,建立的ARIMA模型的拟合精度和预测效果较为理想。结论 ARIMA模型能较好的模拟宝鸡市手足口病的发病趋势,预测效果可信。
OBJECTIVE: To study the trend of HFMD by using time series analysis and to explore a reasonable prediction model to provide decision-making basis for the prevention and control of HFMD in Baoji. Methods The time series analysis method was used to analyze the monthly incidence of HFMD in Baoji from 2008 to 2014 and establish the prediction model. The parameters of the prediction model were estimated, the model was diagnosed, the model was evaluated and the optimal prediction model was selected. The model predicted the incidence in January-June 2015 and evaluated its predictive value. Results The model ARIMA (1,1,1) (0,1,1) 12, R2 = 0.820, normalized BIC = 10.507, Ljung-Box = 4.631 (P = 0.995). The average relative error between predicted and actual monthly incidence of hand-foot-mouth disease was only 2.34% in 2015 and the actual value was within 95% confidence interval. The proposed ARIMA model Amalgamation accuracy and forecasting effect is more ideal. Conclusion The ARIMA model can better simulate the incidence of hand-foot-mouth disease in Baoji City, and the predictive effect is credible.