论文部分内容阅读
目的探索分析手足口病周数据的统计学方法,提升手足口病预测能力。方法中国疾病预防控制信息系统导出2008年第1周至2014年第14周北京市通州区手足口病周发病数。采用SPSS 17.0软件进行自回归、季节性自回归与混合Serfling回归模型拟合。结果自回归、季节性自回归、混合Serfling回归3种模型对2008年第1周至2014年第14周实际发病数进行拟合,回归方程R2分别是0.907、0.917、0.919,所得残差经Ljung-Box检验均是白噪声;以所得回归方程对2014年第15周至第38周实际发病数进行预测,3种模型的平均绝对百分比误差(MAPE)分别为:18.67%、18.43%、17.12%。结论混合Serfling回归模型预测效果最优。
Objective To explore a statistical method to analyze hand-foot-mouth disease data to improve the ability of hand-foot-mouth disease prediction. Methods China Disease Prevention and Control Information System The number of HFMD cases in Tongzhou District of Beijing from the first week of 2008 to the fourteenth week of 2014 was derived. SPSS 17.0 software was used to fit autoregressive, seasonal autoregressive and mixed Serfling regression models. Results Autoregressive, seasonal autoregressive and mixed Serfling regression models fit the actual incidence from the first week of 2008 to the fourteenth week of 2014. The regression equations R2 were 0.907, 0.917 and 0.919, respectively. The residuals were fitted to Ljung- Box test were all white noise. The actual incidence of disease from the 15th week to the 38th week of 2014 was predicted by the regression equation. The mean absolute percentage error (MAPE) of the three models were 18.67%, 18.43% and 17.12% respectively. Conclusion Mixed Serfling regression model has the best prediction effect.