Chapter 7 - Econometric, Gravity, and the 4-Step Methods

Abstract

This chapter deals with econometric, gravity, and the 4-step methods. The successive steps, assumptions, and the necessary conditions for the construction of an econometric model are first described. The selection of the independent variables of an econometric model, of the necessary statistical data, and of its functional form is discussed. The following statistical tests which testify the validity, accuracy, and forecasting ability of an econometric model are presented: stationarity test, Pearson correlation coefficient, calculation of coefficients of the econometric equation, coefficient of determination, tests for the significance of the independent variables, multicollinearity, residuals and outliers, serial correlation, and heteroscedasticity. The distinction between causality and correlation in an econometric model is made. Next, appropriate econometric equations, which permit a causal forecast of future transport demand in relation to the independent variables (some of the driving forces) of the problem, are given for air, rail, road, and public transport (both for passenger and freight) as well as for road safety and taxi services. For each econometric equation, the statistical tests that testify its validity are provided. The 4-step model for the forecast of transport demand at urban level is extensively analyzed afterward. Principles, assumptions, successive steps, and the theoretical basis (on utility theories) of the 4-step model are clarified. Models of trip generation (the first step of the 4-step model) are analyzed (growth factor models, cross-classification models, regression models) with analytical detailed examples. Models of trip distribution (the second step of the 4-step model) are presented (constrained growth factor models, gravity models) with analytical detailed examples. Models for the choice of transport mode (the third step of the 4-step model) are given and more particularly the Logit and Probit models with specific case-study applications. Trip assignment models (the fourth step of the 4-step model) and Wardrop principles are studied; more particularly the all-or-nothing model, the user equilibrium model, and the system optimum model are presented, with specific examples and applications. Finally, the appropriate modeling of freight transport demand (trend projection, application of the 4-step model, econometric and gravity models) is analyzed.