应用指数平滑法预测上海市甲型病毒性肝炎发病趋势

The Application of Exponential Smoothing Methods on the Forecast of Hepatitis A in Shanghai

目的应用指数平滑法拟合和预测本市甲肝疫情。方法分别以1990～2008年按年度和月份的上海市甲肝发病资料数据建立指数平滑模型,以2009年的数据来评价模型的效果。结果上海市甲肝发病趋势明显下降,年发病数据采用Holt趋势指数平滑模型最佳,按月分布发病数使用Holt-Winters相乘模型拟合为最佳,预测模型具有一定的参考意义。结论针对上海市甲肝发病的不同类型数据,均可选用不同指数平滑模型拟合,该方法简单易行,为传染病预测提供了参考。

Objective The application of exponential smoothing methods on the forecast of hepatitis A in Shanghai. Methods To apply exponential smoothing methods on the forecast of hepatitis A in Shanghai by the incidence data of hepatitis A in Shanghai from 1990 to 2008. To set the incidence data in 2009 as the assessment sample of the forecasting effect of the model. Results The incidence trend of hepatitis A in Shanghai declined with fluctuation. Holt trend exponential smoothing method and winters multiplicative exponential smoothing method were respectively chosen in fitness and forecasting in incident rate per year and cases per month of hepatitis A in Shanghai. Conclusion Exponential smoothing methods were simple and applicable tools for fitting the epidemic of hepatitis A and also provided scientific basis for the modeling and forecasting of other infectious diseases.