指数平滑法在南京市艾滋病疫情预测中的应用

Application of exponential smoothing methods on prediction of AIDS epidemic in Nanjing

目的探讨应用指数平滑法预测南京市艾滋病月发病率的可行性,建立艾滋病发病率的预测模型,为制定防治策略提供依据。方法应用SPSS 18.0软件对南京市2006-2012年艾滋病逐月发病率进行模型建模拟合,依据均方根误差和平均绝对误差绝对值最小原则确立最优模型。用所得到的模型对2013年各月发病率进行预测,并与实际发病率进行比较,检验预测效果。结果 Winters可加性模型较好地拟合了艾滋病月发病率的变化规律,模型预测结果与实际值比较接近,实际值均在预测值的95%可信区间范围内。结论 Winters可加性模型能够很好地模拟、预测艾滋病的发病情况,为艾滋病的防治工作提供科学依据。

Objective To explore the feasibility of exponential smoothing methods to predict the AIDS incidence in Nanjing, establish a prediction model for HIV prevalence, and provide a scientific basis for developing prevention and control strategies on AIDS in the future. Methods A model of exponential smoothing methods was established based on the AIDS incidence from January 1,2006 to December 31,2012 in Nanjing, using SPSS18.0 statistical software. And the best model was confirmed through root mean square error（RMSE） and mean absolute percent error （MAPE） which were adapted minimum principle. The constructed model was used to predict the monthly incidence in 2013 and the result was compared with the actual incidence to evaluate prediction effect of exponential smoothing methods. Results The winters additive model fitted the incidence in the previous months, and the forecast values were consistent with the actual numbers which were in the 95%confidence interval of the forecast values. Conclusion The winters additive model could successfully fit and predict the incidence of AIDS in future, which can provide a scientific basis for the prevention and treatment of AIDS.