Application of autoregressive integrated moving average model in incidence rate prediction of hemorrhagic fever with renal syndrome in Shen-zhen city

Objective To establish an autoregressive integrated moving average(ARIMA) model for epidemic trend prediction of hemorrhagic fever with renal syndrome(HFRS)in Shenzhen city.Methods ARIMA model was established based on the monthly incidence rate of HFRS in Shenzhen city from 2005 through 2013.The constructed optimal model was applied to predict the incidence rate of HFRS in Shenzhen city in 2014 and to evaluate the validity of the model through comparing the difference of predicted incidence rate and actual one.The incidence rate of HFRS in 2015 was predicted by the ARIMA model based on the incidence rate from 2005 through 2014.Results The model of ARIMA(1,0,1)(1,0,1)₁₂ had a good fitness to the incidence rate and all parameters(AR=0.993,MA=0.926,SAR=0.967,SMA=0.857)of the model were statistically significant(P<0.01)and Schwarz Bayesian criterion(BIC)=-3.300.The residual error was white noise and the Ljung-Box test statistics for the model was 20.794,with a P value of 0.107.The predicted incidence rate in 2014 was consistent with the actual one,with the relative error of 20.74%.The predicted incidence rate of HFRS in 2015 based on the incidence rate from 2005 through 2014 is 4.28 per billion.Conclusion ARIMA model can be used to simulate changes in HFRS incidence rate and to forecast the incidence rate in future in Shenzhen city.