Exploring the role of utility-difference threshold in choice behavior: An empirical case study of bus service choice

Abstract

This paper provides an empirical case study involving the concept of utility-difference threshold in the context of bus service choice, which aims to explore the role of utility-difference threshold in choice behavior. The underlying assumption is that consumers are unable to recognize a small utility difference between two alternatives, which may be either because they only have imperfect knowledge and limited perception ability or because they just simplify the choice task to save process efforts. Based on this assumption, a concept of utility-difference threshold is introduced to the model specification within which two alternatives are treated as the same. In this study, it is assumed that the utility-difference threshold could be a constant, a random term following a certain distribution or a function of some exogenous determinants, such as consumers’ socio-demographic characteristics. To test these assumptions, a stated choice experiment based on the rule of orthogonality was designed, in which two hypothetical kinds of bus service composing a choice set. A survey based on this design was carried out, in which 1784 valid observations were collected. The estimation results support the existence of utility-difference threshold as well as its observed and unobserved heterogeneity.

Keywords

• Utility-difference threshold
• Bus service choice
• Stated preference experiment
• Heterogeneity