Analysis of Stated Consumer Preferences Using Multinomial Logit Models and Discretechoice R Package

Abstract :

The purpose of the article is to analyze consumer preferences using the selected multinomial logit models consisting of unordered categories. These models are included in the area of microeconometrics and are applied to analyze stated consumer preferences following the approach based on choices and random utility theory. The conducted empirical research was based on the authors’ DiscreteChoice package developed for CRAN R project. The package implements a multinomial, conditional and mixed logit models as well as the functions which can be applied in the discrete choice method for the construction of an experiment, e.g., for a fractional factorial design development, option set coding and model parameter estimation.