Optimal statistical model for forecasting air quality data

The objective of this paper is to apply time series analysis and regression methods to air quality data in order to obtain the optimal statistical model for forecasting. The best estimated model is then used to produce one-step ahead point and interval estimates of future values of the Airborne Particles Index (API) series. API data is analysed using time series analysis, which resulted in an ARMA (2,3) with MADE = 62%. Regression analysis-of this data, using temperature, wind speed and today's API, as explanatory variables, results in MAPE = 42%, which is substantially less than the previous model.