文章摘要
游楠楠,刘 巧,李忠奇,羊海涛.基于ARIMA模型的江苏省不同地区肺结核发病趋势的预测[J].南京医科大学学报,2020,(6):909~914
基于ARIMA模型的江苏省不同地区肺结核发病趋势的预测
Forecast of tuberculosis incidence in different regions of Jiangsu Province based on ARIMA model
投稿时间:2019-08-27  
DOI:10.7655/NYDXBNS20200626
中文关键词: ARIMA模型  时间序列分析  肺结核  预测
英文关键词: ARIMA model  time series analysis  tuberculosis  prediction
基金项目:江苏省研究生科研与实践创新计划项目(KYCX19?1131)
作者单位
游楠楠 东南大学公共卫生学院江苏 南京 210009 
刘 巧 江苏省疾病预防控制中心慢性传染病防制所江苏 南京 210009南京医科大学公共卫生学院流行病与卫生统计学系江苏 南京 211166 
李忠奇 南京医科大学公共卫生学院流行病与卫生统计学系江苏 南京 211166 
羊海涛 东南大学公共卫生学院江苏 南京 210009 
摘要点击次数: 1347
全文下载次数: 483
中文摘要:
      目的:应用差分自回归移动平均(autoregressive integrated moving average,ARIMA)模型对江苏省常州市和盐城市的肺结核发病情况进行预测,探索其用于预测江苏地区肺结核疫情的可行性,为今后结核病防控工作提供参考依据。方法:收集并整理江苏省常州市和盐城市2005年1月—2016年12月肺结核月登记发病数资料,使用R3.5.2软件建立ARIMA模型,分别对两市2017年1—12月肺结核月登记发病数进行预测,以平均绝对百分比误差(mean absolute percent error,MAPE)、均方根误差(root mean square error,RMSE)和平均绝对误差(mean absolute error,MAE)评估ARIMA模型预测的准确性。结果:常州市的最优预测模型为ARIMA(0,1,1)(0,1,1)12,盐城市的最优预测模型为ARIMA(1,1,1)(0,1,1)12。用于预测2017年肺结核月登记发病数时,两市的MAPE分别为8.718 6和16.727 8,RMSE分别为14.061 7和39.487 2,MAE分别为11.381 3和33.349 8。结论:ARIMA模型预测常州市肺结核月登记发病数的拟合效果相对较好,故推测该模型更适用于苏南地区肺结核疫情的短期预测和动态分析。
英文摘要:
      Objective:The autoregressive integrated moving average(ARIMA)model was used to predict the number of registered tuberculosis cases in Changzhou and Yancheng in Jiangsu Province,in order to explore its feasibility for predicting tuberculosis epidemic situation in Jiangsu Province,and provide reference for future tuberculosis prevention and control work. Methods:The data on the number of registered tuberculosis cases in Changzhou and Yanchengof Jiangsu Province from January 2005 to December 2016 were collected,and the ARIMA models were established by the R3.5.2 software. The number of registered tuberculosis cases in January to December 2017 was predicted,with mean absolute percentage error(MAPE),root mean square error(RMSE)and mean absolute error(MAE)to evaluate the accuracy of ARIMA model predictions. Results:The optimal prediction models for Changzhou and Yancheng were ARIMA(0,1,1)(0,1,1)12 and ARIMA(1,1,1)(0,1,1)12,respectively. In the predicted number of registered tuberculosis cases in 2017,the MAPE values of the two cities were 8.718 6 and 16.787 8,the RMSE values were 14.061 7 and 39.487 2,the MAE values were 11.813 1 and 33.349 8,respectively. Conclusion:The ARIMA model has a relatively good fitting effect in predicting the monthly number of registered tuberculosis cases in Changzhou,so it is speculated that the model is suitable for short?term prediction and dynamic analysis of tuberculosis in the southern of Jiangsu.
查看全文   查看/发表评论  下载PDF阅读器