Time series forecasting of quarterly railroad grain carloadings

The participants in the grain logistics system need forecasts of railroad g rain carloads. Although forecasting studies have been conducted for virtual ly every mode, no forecasting studies of quarterly railroad grain transport ation have been published. The objectives of the gaper are (1) specify a US quarterly railroad grain transportation forecasting model, and (2) empiric ally estimate the model. The selection of explanatory variables requires th at they have a theoretical relationship to railroad grain transportation su pply and/or demand, and that the data for the explanatory variables are pub lished in quarterly frequency. However, there are relatively few potential explanatory variables that are published quarterly and those that are avail able appear to have weak correlation with quarterly railroad grain carloadi ngs. The economic process generating quarterly railroad grain carloadings i s quite complex and very difficult to model with regression techniques. Giv en this problem and the focus on short run forecasting, a time series model was employed to forecast quarterly railroad grain carloadings. An AR(4) mo del was estimated using the Maximum Likelihood estimation procedure for the 1987:4-1997:4 period. The actual railroad grain carloadings for this perio d were compared to the forecast carloadings generated by the time series mo del. For 92% of the 37 quarters the percentage difference between the actua l and forecast values was 10% or less. Of the 9 annual observations, the pe r cent difference between the actual and forecast value was less than 2.6% for 8 of the 9 years. (C) 1999 Elsevier Science Ltd. All rights reserved.