ABSTRACT
This chapter presents fundamental concepts of choice theory and reviews two of the most commonly used discrete choice models: the binary logit and the multinomial logit (MNL) models. The four fundamental elements defining a choice scenario: the decision-maker, the alternatives available to the decision-maker, attributes of these alternatives, and the decision rule. The motivation for using maximum utility theory as a decision rule to represent how individuals make trade-offs among attributes. The fact that only differences in utility are uniquely identified influences how variables that do not vary across the choice set should be included in the utility function and imposes the need for normalization requirements on error assumptions. One of the main limitations of the MNL model is the "independence of irrelevant alternatives" or IIA property which states that the ratio of choice probabilities between any two alternatives is independent of the availability or attributes of the other alternatives.
