浙江省食物中毒死亡人数的时间序列分析

Time-series Analysis on the Rate of Death Caused by Food Poisoning in Zhejiang Province

目的探讨应用时间序列ARIMA模型进行食物中毒死亡人数预测的可行性。方法应用时间序列分析1992-2001年浙江省10年各个季度食物中毒发生情况,同时进行ARIMA模型拟合,并用所得的模型对2002-2007年各个季度的食物中毒死亡人数情况进行预测,将预测值与实际值进行比较。结果建立了浙江省食物中毒死亡人数的ARIMA模型方程,显示75.0%实际值在预测值的可信区间内。结论时间序列模型在食物中毒死亡人数预测中具有一定的价值。

Objective To explore the feasibility of autoregressive integrated moving average （ARIMA） model to predict the number of death caused by food poisoning. Methods Time-series analysis was used to construct the ARIMA model based on the death number in Zhejiang province from 1992 to 2001. The constructed model was then applied to predict the number of death caused by food poisoning from 2002 to 2007. Meanwhile, the result from ARIMA model was compared with the actual number so as to evaluate effects of the model. Results The predictive equation on the number of death caused by food poisoning was finally established based on ARIMA model. The curve fitting showed that there was 75.0% actual value in the range of the confidence interval of predictive value. Conclusion The time-series model is proved to be of certain usefulness in the number prediction of death caused by food poisoning.