论文部分内容阅读
目的探讨时间序列模型在甲肝发病预测的应用,为下一步采取防控措施提供科学依据。方法基于宜昌市2005-2015年逐月甲肝发病率建立两种模型,对2016年甲肝的发病率进行预测,并将预测值与实际值进行拟合评价。结果 ARIMA模型首先要求数据平稳,宜昌市的甲肝发病存在季节性波动,为不平稳序列,但2010年之后数据较为平稳,经对2010-2015年甲肝月发病率进行季节性差分、差分处理,新数列为平稳序列(游程检验法Z=1.447,P=0.148),然后进行参数估计(BIC=-4.293)和白噪声检验(Q=22.150,P=0.138),据此建立ARIMA模型,ARIMA(0,0,1)(0,1,1)12模型为最优模型,能较好的模拟甲型病毒性肝炎的发病。结论 ARIMA(0,0,1)(0,1,1)12模型能较好的模拟甲肝发病在时间序列的变化趋势,为制定科学的防控措施和策略提供依据。
Objective To explore the application of time series model in predicting the occurrence of hepatitis A and provide a scientific basis for further prevention and control measures. Methods Based on the monthly incidence of hepatitis A in Yichang City from 2005 to 2015, two models were established to predict the incidence of hepatitis A in 2016. The predictive value and the actual value were fitted and evaluated. Results ARIMA model first requires stable data. There is a seasonal fluctuation in the incidence of hepatitis A in Yichang City, which is an unstable sequence. However, the data after 2010 are relatively stable. After a seasonal difference and differential treatment of the monthly incidence of hepatitis A from 2010 to 2015, (BIC = -4.293) and white noise test (Q = 22.150, P = 0.138). Based on this, ARIMA model (0 , 0,1) (0,1,1) 12 model as the best model, can better simulate the onset of viral hepatitis A. Conclusion The ARIMA (0,0,1) (0,1,1) 12 model can better simulate the trend of hepatitis A in time series, and provide the basis for making scientific prevention and control measures and strategies.