Forecasting intercity commodity transport in the U.S.A.

Publisher Website
Google Scholar
Abstract
O'Sullivan P. and Ralston B. (1974) Forecasting intercity commodity transport in the U.S.A., Reg. Studies 8, 191–195. The merits of a production constrained gravity model, regression and linear programming formulations in forecasting the distribution of food and animal products between 25 metropolitan areas in the U.S. are tested using 1963 and 1967 Census of Transportation data. The differences between actual trade flows and those estimated by each model are examined in terms of overall error and the distribution of error by distance and volume categories. The linear programming model is marginally superior to the gravity model and both are more accurate than the regression model. The parameters of the gravity and regression models were estimated with 1963 and 1967 data and the differences in the two time periods proved statistically insignificant for the most part.

This publication has 2 references indexed in Scilit: