Discrete Choice Modelling and Air Travel Demand: Theory and Applications

摘要

Discrete choice models became popular in the 1970s when Nobel Prize winner Daniel McFadden and other economists tried better to understand commuters' preferences for specific modes of transportation in the San Francisco Bay area. A discrete choice model refers to a mathematical function that predicts an individual's choice based on the utility or relative desirability of competing alternatives. The popularity of discrete choice models underlined the shift from modelling demand with aggregate data to estimating it as a collection of individual choices. Usually, a choice process is characterised by four elements: the decision-maker, the alternatives, the attributes of the alternatives, and the decision rule. Discrete choice models can be classified into several categories based on the number of alternatives under consideration, the assumed distribution of the error terms and the independence from irrelevant alternatives.