中文摘要：

目的探讨应用时间序列求和自回归移动平均（ARIMA）模型预测艾滋病发病率的可行性。方法利用重庆市疾病控制部门提供的1993～2009年艾滋病发病情况数据建立ARIMA预测模型。结果 ARIMA（1,1,1）×（0,1,0）12很好地拟合了艾滋病发病率,2009年7～12月的预测值符合实际发病率变动趋势。结论 ARIMA模型很好地模拟艾滋病发病率在时间序列上的变动趋势,可以为疫情防控提供借鉴。

英文摘要：

Objective To explore the feasibility of auto regressive integrated moving average（ARIMA）model of time series to predict the incidence of AIDS.Methods The ARIMA model was established basing on the data of AIDS incidences in Chongqing during 1993-2009.Results The model of ARIMA（1,1,1）×（0,1,0）12 exactly fitted the incidence of AIDS.The predicting values of incidence in July to December 2009 were consistent with the actual change trend of incidence.Conclusion The ARIMA model can be used to exactly simulate the change trend of the incidence of AIDS in time series,which can provide reference for prevention and control of AIDS.