摘要
目的 利用自回归滑动平均混合（ARIMA）模型预测长沙市流感样病例（ILI）的发病趋势. 方法 收集长沙市2006年第1周-2013年第10周由流感监测哨点医院每日报告的流感样病例监测资料,进行时间序列分析并建立预测模型,使用前364周资料建立模型,后10周资料评估模型预测效果. 结果 流感样病例监测资料构建ARIMA（1,0,0）模型,回归系数差异有统计学意义（P＜0.05）.白噪声残差分析显示序列自相关函数的Box-Ljung统计量最小值为20.155（P＞0.05）,残差为随机性误差.1-364周资料所建立模型ARIMA（1,0,0）预测效果良好,实际值均在预测值的95％可信区间（95％ CI）内,符合率达100％.2013第11-16周长沙市ILI％预测值分别为2.28％（95％CI：0.00％～6.21％）、2.31％（95％ CI：0.00％ ～6.26％）、2.33％ （95％CI：0.00％ ～6.30％）、2.35％ （95％ CI：0.00％ ～6.33％）、2.36％ （95％ CI：0.00％ ～6.35％）、2.38％ （95％CI：0.00％～6.37％）. 结论 ARIMA模型能较好模拟长沙市流感样病例的发病趋势.
Objective To forecast the incidence trend of influenza- like illness （ILl） in Changsha by using autoregressive integrated moving average （ARIMA） model. Methods The surveillance data of daily reports of influetma - like illness from 1st week, 2006 to 10th week, 2013 were collected, Time series analysis was made and the prediction model was established. The data of the early 364 weeks were used to establish the model and those of the later 10 weeks were used to evaluate the prediction efficiency of the modal. Results The regression coefficient of the model ARIMA（1,0,0） established from the surveillance data has statistical significance（ P 〈 0.05）. Analysis of white - noise residual of model showed that the the minimum Box - Ljung value of the autocorrdation function was 20. 155 （ P 〉0.05 ） and the residual was randomized difference. The model ARIMA（ 1, 0,0） basesd on the data of the 1st - 364th week had good performance in prediction. The actual values all fell within the 95 % CI of the predicted values, and the coincidence rate was up to 100%. The predicted values of ILI% in Changsha from the 11 lh to 16th week, 2013 were 2.28%（95%CI：0.00% -6.21%）, 2.31%（95%CI：0.00% -6.26%）, 2.33% （95% CI：0.00% 6.30%）, 2.35%（95%CI：0.00%-6.33%）, 2.36%（95%CI：0.00%-6.35%） and 2.38%（95%CI：0.00%-6.37%）, respectively. Conclusions ARIMA model can well simulate the incidence trend of influenza - like illness in Changsha.
出处
《实用预防医学》
CAS
2013年第9期1052-1055,共4页
Practical Preventive Medicine
基金
湖南省卫生厅科研课题(B2012-138)
长沙市科技局科研课题(K1205028-31)
关键词
流感样病例
模型
统计学
时间序列
Influenza - like illness
Model
Statistics
Time series
