论文部分内容阅读
目的:探讨应用时间序列SAR IM A模型进行肾综合征出血热发病率预测的可行性.方法:首先利用余弦函数模型分析肾综合征出血热季节性发病规律,其次进行扩充迪基富勒的平稳性单位根检验,然后根据自相关函数和偏自相关函数判别月别疫情间的相关性,最后基于1990年-2004年逐月发病率进行SAR IM A模型建模拟合,利用2005年各月发病率进行外推预测,并与实际值进行比较.上述统计分析采用Ev iew s3.1和SPSS12.0软件完成.结果:余弦函数确定的高峰时点为3月中旬,高峰时区为3月1日到4月3日.含第一谐量的余弦方程为:^Y1 i=1.274-0.945cos(ti-76.684),决定系数R2=0.853;在备选模型中,SAR IM A(1,0,0)×(2,0,0)12模型不仅很好地拟合了既往时间段上的发病率序列,而且对2005年各月发病率的预测值符合实际发病率变动趋势.结论:余弦函数对于褐家鼠型肾综合征出血热疫情季节分布拟合较好,SAR IM A模型能很好地模拟传染病发病率在时间序列上的变动趋势,并对未来的发病率进行预测,为传染病防制工作服务.
Objective: To explore the feasibility of using time series SAR IM A model to predict the incidence of hemorrhagic fever with renal syndrome.Methods: Firstly, the seasonal incidence of hemorrhagic fever with renal syndrome was analyzed by cosine function model, followed by the expansion of Dickey fuller’s stability Sex unit root test, then according to the autocorrelation function and the partial autocorrelation function to discriminate the correlation between the monthly epidemic outbreaks, and finally based on monthly incidence from 1990 to 2004 SAR IM A model modeling and fitting, the use of each month in 2005 Incidence was extrapolated to predict and compared with the actual value of the above statistical analysis using Ev iew s3.1 and SPSS12.0 software.Results: The cosine function to determine the peak time for the mid-March, the peak time zone for March 1 Day to April 3. The cosine equation with the first harmonic is: ^ Y1 i = 1.274-0.945 cos (ti-76.684) with a determination coefficient R2 = 0.853; in the alternative model, SAR IM A (1,0 , 0) × (2, 0, 0) 12 The model not only fit well the past incidence of the time series, but also predict the monthly morbidity in 2005 according to the trend of actual incidence.Conclusion: Function fitted better seasonal distribution of hemorrhagic fever with Rattus norvegicus syndrome, SAR IM A mode The model can well simulate the trend of the change of the incidence of infectious diseases in time series and predict the future incidence and serve the prevention and control of infectious diseases.