Combining Linear And Nonlinear Model In Forecasting Railway Passenger Volume

The estimate for railway passenger volume is the important foundation and the main evidence for railway transportation. Before an important strategy made by Railway Company, an estimate for railway passenger volume usually has been done. It can ensure to make scientific decision, workout feasible plan and layout and development strategies. At present, there are many models for railway passenger volume forecast, but a unitary model cannot reflect the movement rule and information of railway passenger volume. We will use combination model to forecast the railway passenger volume in order to improve the precise.Much research shows that combining forecasts improves accuracy relative to individual forecasts. However, existing forecasting related literature shows that combined forecasts from a linear and a nonlinear model can improve forecasting accuracy. This paper combined the linear and nonlinear statistical models to forecast time series with possibly nonlinear characteristics. Real time series data sets of railway passenger volume were used to examine the forecasting accuracy of the combination models. The forecasting performance was compared among three individual models and six combination models, respectively. Among these models, the normalized mean square error (NMSE) and the mean absolute percentage error (MAPE) of the combination models were the lowest. Thus, this paper suggests that forecast combination can achieve considerably better predictive performances in the railway passenger volume context.