ARIMA模型在我国梅毒发病率预测中的应用  

Application of ARIMA model in prediction of incidence of syphilis in China

作　　者：王永斌[1] 李向文[1] 柴峰[1] 袁聚祥[1] 

机构地区：[1]河北联合大学公共卫生学院,河北唐山063000

出　　处：《现代预防医学》2015年第3期385-388,417,共5页Modern Preventive Medicine

摘　　要：目的探索ARIMA模型在我国梅毒发病率预测中的应用,为提出相应的预防措施提供依据。方法收集2004年1月-2012年12月我国梅毒发病率资料,用SPSS13.0拟合ARIMA模型,并用2013年每月的数据评价模型的预测效果。结果 ARIMA(1,1,0)×(2,1,1)12模型为预测我国梅毒发病率的最佳模型,预测值和实际值的动态趋势基本一致。并用此模型对2014年每月我国梅毒发病率进行了预测。结论 ARIMA模型是一种短期内预测精度较高的预测模型,预测效果可靠。Objective To explore the application of ARIMA model in the prediction of incidence of syphilis in China and provide basis for making corresponding preventive measures. Methods The data of incidence of syphilis from January 2004 to December 2012 in China was collected and SPSS13.0 was used to fit the ARIMA model. At the same time, the monthly data in 2013 was used to validate the effect of prediction. Results ARIMA（1, 2, 0）×（0, 1, 1）12 model was the best model in forecasting incidence of syphilis in China. The dynamic tendency of the predicted value and the actual value were basically the same. The model was used to forecast monthly incidence of syphilis in 2014 in China. Conclusion ARIMA model is a forecasting model with high accuracy, and its forecasting effect is reliable in the short term.

关 键 词：ARIMA模型 梅毒 发病率 预测 

分 类 号：R195[医药卫生—卫生统计学]