摘要
搜集2008-2014年新疆巴音郭楞蒙古自治州(简称巴州)梅毒月发病数据,采用时间序列分解方法(Time Series Decomposition methods)探讨该地区梅毒月发病率的季节性,建立ARIMA(0,1,1)(1,0,1)_(12)时间序列模型,模型预测值的动态趋势与实际发病率基本吻合,平均绝对百分比误差MAPE=17.36,具有较高的预测精度,可以较好的预测短期内梅毒的变化趋势,为梅毒的预防控制措施提供可靠依据.
Based on the data of syphilis monthly cases during 2008-2014 to explore the trend and seasonal apply the time series decomposition methods according the monthly incidence of syphilis in Bazhou,and we try to establish ARIMA（0,1,1）（1,0,1）12 time series model,which had high precision and the predicted value was close to the true incidence.The Mean Absolute Percentage Error（MAPE） is 17.36.It may be useful to apply the ARIMA model to predict the incidence tendency of syphilis in short time,and provide evidence for the development of syphilis control and prevention measures.
出处
《数学的实践与认识》
北大核心
2017年第7期111-117,共7页
Mathematics in Practice and Theory
基金
国家自然科学基金(11461073)
