Prediction of Incidence for Water-borne Diseases on a Multiple Seasonal ARIMA Model in Suzhou

Objectives To explore the application of a multiple seasonal autoregressive integrated moving average (ARIMA) model in predicting the incidence of water-borne diseases in Suzhou.

Methods A multiple seasonal ARIMA model based on the incidence of water-borne diseases in Suzhou from 2008 to 2015 was established by the R software, an optimal fitted model was then used to predict the incidence of water-borne diseases in Suzhou from January to June in 2016.

Results A multiple seasonal ARIMA (2, l, 2)×(0, l, 1)₁₂ model was established. There was no statistically significant difference in fitting effect(Q=18.478, P=0.779)tested by the Ljung-Box test, and the model was fitted for forecasting a short term incidence rate, all actual values of the incidence of water-borne diseases in Suzhou from January to June in 2016 were in the 95% confidence intervals of predicted values, the mean relative error was -0.024.

Conclusion Multiple seasonal ARIMA (2, l, 2)×(0, 1, 1)₁₂ model could be used to predict the short term incidence rate of water-borne diseases in Suzhou.