Dengue is one of the major public health problems in the tropical countries of the world. SARIMA model is a popular method used for forecasting dengue incidence. The aim of this study was to determine optimal model for forecasting the dengue incidence. SARIMA model with Box-Jenkins approach was conducted to forecast dengue incidence using the previous data from 2006 to 2015. Akaike’s Information Criteria (AIC), Bayesian Information Criteria (BIC) and Root Mean Square Error (RMSE) were used to determine their accuracy. The results showed that SARIMA (6, 0, 3) (0, 1, 1)52 were the best model that fitted with the actual data. It had the smallest AIC and BIC (3827.60 and 3873.30, respectively) and RMSE (0.8420).
Keywords: dengue incidence, SARIMA, forecasting model
*Corresponding author: Tel.: +66-2354-8530 Fax: +66-2354-8534
E-mail: jutatip.sil@mahidol.ac.th
