Forecasting Dengue Fever Cases in Guangdong Province Using SARIMA Model

Guangdong Province is the area with the highest incidence of DF in China. Predicting the incidence of DF accurately is meaningful for improving contingency planning of public health interventions. In this study, Seasonal Autoregressive Integrated Moving Average (SARIMA) model was developed on the data of monthly number of new cases of DF between May 2sg008 and December 2012, and then validated the models using the data between January and April 2013. The data were fitted well using a final SARIMA(1, 0, 0)(0, 1, 0) 24 model. The results showed that the predicted values were consistent with the pattern of observed values, with the root mean square error (RMSE) of the time series fitted equaling 19.9 and the RMSE of the time series forecasted equaling 3.2. Thus, SARIMA is useful for predicting DF incidence.