深圳市肾综合征出血热时间序列预测分析

Time series predicting the epidemic tendency of HFRS in Shenzhen

目的利用拟合ARIMA模型对深圳市肾综合征出血热(HFRS)的发病趋势进行时间序列分析和预测,为制定HFRS防治策略提供科学依据。方法收集深圳市2005—2014年HFRS季度发病资料,通过SPSS 19.0软件拟合ARIMA模型,预测2015年各季度的发病数。结果最终拟合为ARIMA(0,0,0)(0,1,1)4模型,残差为白噪声序列,预测值与实际值的平均相对误差为28.6%。2015年各季度HFRS发病的预测值符合实际值的变动趋势。结论 ARIMA模型能较好模拟深圳市HFRS的发病趋势。

Objective To analyze and predict incidence of hemorrhagic fever with renal syndrome （HFRS） in Shenzhen with an auto regressive integrated moving average （ARIMA） model, which may provide a scientific basis for developing prevention and control strategies on HFRS in the future. Methods Incidence of HFRS was collected quarterly from 2005 to 2014 and a model （ARIMA） was fit with SPSS 19.0 software, to predict the incidence of HFRS from the I quarter to IV quarter 2015.Results The model ARIMA （0, 0, 0） （ 0, 1, 0） 4 was established finally and the residual sequence was a white noise sequence. The relative error in average was 28.6% between the forecasting value and the real value. The predicted incidence in 2015 was consistent with the actual one. Conclusion ARIMA model can predict the trend of HFRS in Shenzhen.