Application of ARIMA model for prediction of incidence of scarlet fever

Objective To evaluate the performance of multiple seasonal autoregressive integrated moving average (ARIMA) model in the prediction of scarlet fever incidence in Jinan, and provide evidence for the prevention and control of the disease. Methods The incidence data of scarlet fever in Jinan from 2006 to 2014 were used to establish ARIMA model and the incidence data in Jinan from January to June in 2015 were used to evaluate the accuracy of the model. The incidence of scarlet fever in Jinan in 2105 was predicted by using the model. Results ARIMA (1,0,0)(0,1,1)12 model could be used to predict epidemiological tendency of scarlet fever in Jinan. The R2 of the model was 0.64. Conclusion The incidence of scarlet fever in Jinan was still at high level in 2015. It is necessary to strengthen the scarlet fever surveillance to prevent the outbreak of scarlet fever.