应用灰色模型和指数平滑法预测上海市肾综合征出血热发病率  

Application of Grey Model(1,1) and Exponential Smoothing Method in Forecasting Hemorrhagic Fever with Renal Syndrome in Shanghai

作　　者：朱奕奕[1,2] 李燕婷[1] 王晔[1] 冯玮[1] 顾宝柯[1] 袁政安[1] 

机构地区：[1]上海市疾病预防控制中心,上海200336 [2]复旦大学公共卫生学院,上海200032

出　　处：《环境与职业医学》2010年第9期528-531,共4页Journal of Environmental and Occupational Medicine

基　　金：上海市卫生局青年科研基金项目(编号:054Y13)

摘　　要：[目的]预测上海市肾综合征出血热的发病趋势。[方法]利用上海市肾综合征出血热发病资料,建立灰色模型和指数平滑模型来预测本市未来肾综合征出血热的发病率。[结果]上海地区肾综合征出血热发病率(×10-5)的灰色预测模型为:=(1.49-2.3669/0.5823)e-0.5823t+2.3669/0.5823,拟合检验显示本模型精度等级为一级,能够较好地预测上海市肾综合征出血热发病率;Holter-Winters双参数指数平滑法预测的最小误差平方和与均方根误差最小,通过D-W检验,预测效果较好。[结论]两种方法均可应用于上海市肾综合征出血热发病率的预测。[ Objective] To forecast the trend of incident rate of Hemorrhagic Fever with Renal Syndrome（HFRS）in Shanghai.[ Methods] Grey model（1, 1）and Exponential Smoothing model were applied to forecast incident rate of HFRS in Shanghai.[ Results] Grey model（1, 1）forecast equation was =（1.49-2.3669/0.5823）e-0.5823t＋2.3669/0.5823 and fitness test analysis showed that Grey model was a good model for incident rate forecasting. By comparing sum of squared residuals and root mean squared error, Holter-Winters Exponential Smoothing forecasting was a best Exponential Smoothing method for HFRS, and D-W test also certificated to it.[ Conclusion] Both Grey model（1, 1）and Holter-Winters Exponential Smoothing method are both suitable for forecasting HFRS incident rate.

关 键 词：灰色模型 指数平滑法 预测 

分 类 号：R183[医药卫生—流行病学]