Modelling indefference option in stated preference surveys

Abstract

An efficient choice design is characterized by utility balance, that is, the alternatives defined within each choice set have more or less equal choice probabilities. In these cases, respondents should be as nearly indifferent as possible. We propose a discrete choice model that describes the behaviour of individuals with indifference thresholds; this makes them perceive similar utilities from a specific situation in a stated preference (SP) experiment. The proposed model considers two alternatives plus the indifference option, so that the individual is not forced to choose one of the alternatives if s/he finds them equally attractive. We postulate that if thresholds exist they could be stochastic, random, differ among the population and even be a function of socio-economic characteristics and choice conditions. Our formulation allows estimation of the parameters of the threshold probability distribution starting from information about choices. As an illustration, the model was applied to synthetic and to real data coming from a stated preference survey; results show that when indifference thresholds exist in the population, the use of models without considering them can lead to errors in model estimation as well in prediction.