摘要
本文研究乘积季节模型在传染病发病情况预测中的应用,并探讨提高模型准确性和实用性的途径.以1980年1月至2000年7月江苏省肾综合征出血热发病资料建立模型,以2000年的发病资料作为模型预测效果的考核样本.首先采用差分方法对序列资料进行平稳化,然后进行定阶并估计参数,建立乘积季节模型,最后对预测结果进行检验和分析.从而更好地掌握未来疫情动态发展趋势.检验结果表明,用乘积季节模型对肾综合征出血热月发病情况的拟合结果满意,预测效果良好.
To research the application of ARIMA product season model forecasting in infectious disease incidence, and discuss the method to improve its veracity and practicability. Model was fitted by the historical data of HFRs of Jiangsu Province. Firstly, used the difference method to make the data sequence become placid. Secondly, parameters of model is estimated and set up a product season model by decide the rank of it. Finally, the paper tests the result of forecast and analysis it. So we can predominate the trends of epidemic situation better than before. It is practical to apply the approach of ARIMA product season model to predict HFRs in Jiangsu Province by test.
出处
《数理统计与管理》
CSSCI
北大核心
2008年第2期362-368,共7页
Journal of Applied Statistics and Management
基金
江苏省社会发展基金资助(BS2000043)
江苏省卫生科研项目资助(Y200429)
