ARIMA乘积季节模型在河北省唐山市布鲁氏菌病发病预测中的应用
|
摘要
目的了解唐山市2007-2017年布鲁氏菌病(简称布病)月发病数的趋势性和季节性,建立布病分析模型,为布病短期预测与防治提供决策依据。方法收集唐山市2007-2017年布病月发病人数,构建ARIMA乘积季节模型,并进行短期预测预报。结果唐山市2007-2017年布病疫情呈逐步上升趋势,尤其2013年后大幅攀升。从季节性来看,每年的5～7月为发病高峰。选取的最优模型为ARIMA(0,1,0)(1,1,0) 12。运用此模型对2018年1～6月唐山市布病月发病数进行预测,各月预测值分别为11、12、16、16、24、20例。结论 ARIMA乘积季节模型拟合唐山市布病月发病数的时间序列模型精度较高,适合唐山市布病发病数的短期预测。
Objective To investigate the trend and seasonality of monthly prevalence of brucellosis from 2007 to 2017 in Tangshan,and to establish multiple seasonal Autoregressive Integrated Moving Average( ARIMA) model to provide a reference for the prevention and control of brucellosis. Methods The number of cases of brucellosis in Tangshan City from 2007 to 2017 was collected,the multiple seasonal ARIMA model was constructed,and short-term prediction was carried out. Results From 2007 to 2017,the prevalence of brucellosis showed a gradual upward trend,especially after 2013. From the perspective of seasonality,the peak incidence period was from May to July each year. The optimal model selected was ARIMA( 0,1,0)( 1,1,0) 12. This model was used to predict the monthly prevalence of the brucellosis from January to June in 2018 using ARIMA( 0,1,0)( 1,1,0) 12. The predicted prevalence of each month was 11,12,16,16,24 and 20 respectively. Conclusion Multiple seasonal ARIMA model has a high precision in fitting the time series model of monthly prevalence of brucellosis in Tangshan and can be used for short-term prediction of monthly prevalence of brucellosis in Tangshan.
Objective To investigate the trend and seasonality of monthly prevalence of brucellosis from 2007 to 2017 in Tangshan,and to establish multiple seasonal Autoregressive Integrated Moving Average( ARIMA) model to provide a reference for the prevention and control of brucellosis. Methods The number of cases of brucellosis in Tangshan City from 2007 to 2017 was collected,the multiple seasonal ARIMA model was constructed,and short-term prediction was carried out. Results From 2007 to 2017,the prevalence of brucellosis showed a gradual upward trend,especially after 2013. From the perspective of seasonality,the peak incidence period was from May to July each year. The optimal model selected was ARIMA( 0,1,0)( 1,1,0) 12. This model was used to predict the monthly prevalence of the brucellosis from January to June in 2018 using ARIMA( 0,1,0)( 1,1,0) 12. The predicted prevalence of each month was 11,12,16,16,24 and 20 respectively. Conclusion Multiple seasonal ARIMA model has a high precision in fitting the time series model of monthly prevalence of brucellosis in Tangshan and can be used for short-term prediction of monthly prevalence of brucellosis in Tangshan.
引文
[1]施旭光,凌锋.布鲁氏菌病研究进展[J].浙江预防医学,2014,26(6):576-580.
[2]高雯,张志坤,王建红,等.唐山市1977-2016年人间布鲁菌病疫情监测分析[J].现代预防医学,2018,45(1):137-140.
[3]WU W,GUO J,AN S,et al.Comparison of two hybrid models for forecasting the incidence of hemorrhagic fever with renal syndrome in Jiangsu Province,China[J].PLo S One,2015,10(8):e0135492.
[4]JEBB AT,TAY L,WANG W,et al.Time series analysis for psychological research:examing and forecasting change[J].Front Psychol,2015,6(9):727.
[5]高光俊,徐杰,柯跃华,等.我国近10年布鲁氏菌病研究文献分析[J].中国人兽共患病学报,2012,28(12):1178-1184.
[6]范蒙光,塔娜,郭威,等.2010-2014年内蒙古自治区人间布鲁氏菌病监测结果分析[J].疾病监测,2016,31(11):945-948.
[7]杨旭欣,秦豫民,马丽,等.青海省2009-2014年人间布鲁氏菌病调查结果分析[J].中国媒介生物学及控制杂志,2016,27(4):378-380.
[8]朱连开,梁文佳,陈经雕.广东省2004-2010年布鲁氏菌病流行特征分析[J].华南预防医学,2012,38(4):45-46.
[9]霍爱梅,赵达生,方立群,等.华北地区自然疫源性疾病的分布及其与气象条件的关系[J].中国病原生物学杂志,2011,6(1):5-9.
[10]王永斌,李向文,柴峰,等.ARIMA模型在我国梅毒发病率预测中的应用[J].现代预防医学,2015,42(3):385-388.
[11]姚英,沈毅.手足口病发病趋势的ARIMA模型预测[J].浙江预防医学,2015,27(2):147-149.
[12]晁灵,冯晖,桂立辉.2009-2013年焦作市流行性腮腺炎流行特征分析及ARIMA预测[J].现代预防医学,2015,42(6):966-969.
[13]孙振球.医学统计学[M].4版.北京:人民卫生出版社,2014:661-679.
[14]田德红,丁国武,于国伟,等.自回归求和移动平均乘积季节模型在我国布鲁菌病短期月发病人数预测中的应用[J].中国全科医学,2015,33(18):4100-4104.
[15]LEE HS,HER M,LEVINE M,et al.Time series analysis of human and bovine brucellosis in South Korea from 2005 to 2010[J].Preventive Veterinary Medicine,2013,110(2):190-197.
[2]高雯,张志坤,王建红,等.唐山市1977-2016年人间布鲁菌病疫情监测分析[J].现代预防医学,2018,45(1):137-140.
[3]WU W,GUO J,AN S,et al.Comparison of two hybrid models for forecasting the incidence of hemorrhagic fever with renal syndrome in Jiangsu Province,China[J].PLo S One,2015,10(8):e0135492.
[4]JEBB AT,TAY L,WANG W,et al.Time series analysis for psychological research:examing and forecasting change[J].Front Psychol,2015,6(9):727.
[5]高光俊,徐杰,柯跃华,等.我国近10年布鲁氏菌病研究文献分析[J].中国人兽共患病学报,2012,28(12):1178-1184.
[6]范蒙光,塔娜,郭威,等.2010-2014年内蒙古自治区人间布鲁氏菌病监测结果分析[J].疾病监测,2016,31(11):945-948.
[7]杨旭欣,秦豫民,马丽,等.青海省2009-2014年人间布鲁氏菌病调查结果分析[J].中国媒介生物学及控制杂志,2016,27(4):378-380.
[8]朱连开,梁文佳,陈经雕.广东省2004-2010年布鲁氏菌病流行特征分析[J].华南预防医学,2012,38(4):45-46.
[9]霍爱梅,赵达生,方立群,等.华北地区自然疫源性疾病的分布及其与气象条件的关系[J].中国病原生物学杂志,2011,6(1):5-9.
[10]王永斌,李向文,柴峰,等.ARIMA模型在我国梅毒发病率预测中的应用[J].现代预防医学,2015,42(3):385-388.
[11]姚英,沈毅.手足口病发病趋势的ARIMA模型预测[J].浙江预防医学,2015,27(2):147-149.
[12]晁灵,冯晖,桂立辉.2009-2013年焦作市流行性腮腺炎流行特征分析及ARIMA预测[J].现代预防医学,2015,42(6):966-969.
[13]孙振球.医学统计学[M].4版.北京:人民卫生出版社,2014:661-679.
[14]田德红,丁国武,于国伟,等.自回归求和移动平均乘积季节模型在我国布鲁菌病短期月发病人数预测中的应用[J].中国全科医学,2015,33(18):4100-4104.
[15]LEE HS,HER M,LEVINE M,et al.Time series analysis of human and bovine brucellosis in South Korea from 2005 to 2010[J].Preventive Veterinary Medicine,2013,110(2):190-197.