TIME SERIES FORECASTING OF QUARTERLY BARGE GRAIN TONNAGE ON THE MCCLELLAN-KERR ARKANSAS RIVER NAVIGATION SYSTEM

Although forecasting studies have been conducted for virtually every mode, no forecasting studies of quarterly barge grain transportation have been published. The intent of this paper is to remedy that omission and develop a forecasting model for grain tonnage on the McClellan-Kerr Arkansas River Navigation System. The objectives of the study are (1) specify a quarterly forecasting model for Arkansas River soybean and wheat tonnage, and (2) empirically estimate the two models developed in objective 1. The selection of explanatory variables requires that they have a theoretical relationship to barge grain transportation supply and/or demand, and that the data for the explanatory variables are published in quarterly frequency. However, there are relatively few potential explanatory variables that are published quarterly and those that are available appear to have weak correlation with quarterly barge grain tonnage. The economic process generating quarterly barge grain tonnage is quite complex and very difficult to model with regression techniques. Given this problem and the focus on short run forecasting, a time series model was employed to forecast deseasonalized quarterly McClellan-Kerr Arkansas River soybean and wheat tonnage. An AR (8) model was estimated using the Maximum Likelihood estimation procedure for the 1991:2 - 1999:3 period to forecast deseasonalized quarterly McClellan-Kerr Arkansas River soybean tonnage. An ARMA (2,8) model was estimated using the Maximum Likelihood estimation procedure for the 1991:2 - 1999:3 period to forecast deseasonalized quarterly McClellan-Kerr Arkansas River wheat tonnage. The actual McClellan-Kerr Arkansas River deseasonalized soybean and wheat tonnage for this period were compared to the forecast tonnage generated by the time series models. For the McClellan-Kerr Arkansas River soybean tonnage model, of the 7 annual observations, the percentage difference between the actual and forecast value is less than 8.5 percent for 6 of the 7 years. Of the 7 annual observations, the percentage difference between the actual and forecast value is less than 10 percent for 5 years for the McClellan-Kerr Arkansas River wheat tonnage model.

• Corporate Authors:

  Transportation Research Forum

  One Farragut Square South, Suite 500
  Washington, DC  United States  20006-4003
• Authors:
  • Tang, Xiuli
• Conference:
  • Proceedings of the 42nd Annual Meeting of the Transportation Research Forum
  • Location: Annapolis, Maryland
  • Date: 2000-11-29 to 2000-12-1
• Publication Date: 2000

Language

• English

Media Info

• Features: Figures; References; Tables;
• Pagination: p. 129-159

Subject/Index Terms

• TRT Terms: Barge carriers; Data collection; Forecasting; Grain; Navigation; Service time; Soybeans; Time series; Tonnage; Wheat
• Geographic Terms: Arkansas
• Subject Areas: Marine Transportation; Operations and Traffic Management;

Filing Info

• Accession Number: 00804774
• Record Type: Publication
• Files: TRIS
• Created Date: Jan 10 2001 12:00AM