This study aimed to provide an Auto-Regressive Integrated Moving Average (ARIMA) model that can predict dengue incidence in Magalang, Pampanga based on the past dengue incidences & climate variables from 2016 to 2019 and identify significant predictor/predictors among the climate variables. Weekly dengue incidence and climatological data from January 2016 to December 2019 were gathered and considered as the dependent and independent variables, respectively. Then, the Expert Modeler in IBM SPSS 22 automatically selected and estimated the best fitting ARIMA model for one dependent variable series. The created model was then used to forecast dengue incidence for the 52-week period of 2020, employing quarterly, semi-annual, and annual forecasting. A one-way ANOVA was conducted to evaluate differences among the four groups, followed by a post hoc Scheffe test to determine which groups differed from each other. Additionally, the Diebold-Mariano (DM) test was utilized to validate the forecasting performance of the ARIMA model. The non-seasonal ARIMA (0,1,6) model, with the sum of rainfall as the sole predictor from seven candidate predictors, was identified as the best fit. Model fit statistics indicated a stationary R-squared value of 0.739. The Ljung-Box statistics test value of 0.344, deemed not significant, confirmed correct model specification. One-way ANOVA analysis revealed a significant difference among the four groups, with an F value of 34.37 and a p-value approaching zero. Post hoc Scheffe tests further indicated a significant difference between the observed dataset and both semi-annual and annual forecasting, with p-values of 0.014 and approaching zero, respectively. However, no significant difference was observed between the observed dataset and quarterly forecasting, with a p-value of 0.281. Moreover, DM test statistics revealed that quarterly forecasting outperformed both annual and semi-annual forecasting. This suggests that the non-seasonal ARIMA (0,1,6) model, with the sum of rainfall as a predictor, effectively predicts future dengue incidences using quarterly forecasting.
Read full abstract