Zhou Chunbei, Yao Ning. Application of autoregressive integrated moving average model(ARIMA) in the prediction of Japanese encephalitis in Chongqing[J]. Journal of Chongqing Medical University, 2017,42(10):1345-1349.
Zhou Chunbei, Yao Ning. Application of autoregressive integrated moving average model(ARIMA) in the prediction of Japanese encephalitis in Chongqing[J]. Journal of Chongqing Medical University, 2017,42(10):1345-1349. DOI: 10.13406/j.cnki.cyxb.001372.
Objective:To predict the possible Japanese encephalitis(JE)cases in Chongqing using autoregressive integrated moving average model(ARIMA). Methods:An ARIMA prediction model was established by R software using data of reported JE cases in Chongqing from January 2006 to June 2015. Comparison between predicted numbers and reported cases from July to December of2015 was examined for model assessment
then the most fitted model was used to predict JE cases in year 2016-2017. Results:Reported JE cases in Chongqing decreased annually
and fit the characteristic of seasonal change. ARIMA(0
0
1)×(1
1
2)12can appropriately fit the time series with the smallest value of Akaike information criterion(AIC)and Schwarz Bayesian criterion(SBC)index with a mean relative residual of 0.12
the mean absolute percentage error(MAPE)was 7.81%. The predicted JE cases in year2016 and 2017 were 35 and 32 respectively
the incidence peak was still at July and August. Conclusion:The ARIMA model can be used to fit the time series trend of JE disease
predicted JE cases in year 2016 and 2017 would be less than that of reported cases in2015.
关键词
流行性乙型脑炎自回归求和移动平均乘积季节模型预测
Keywords
Japanese encephalitismultiple seasonal ARIMA modelprediction