Estimating Common Utility Origins and Scales in DiscreteChoice Conjoint with Auxiliary Data Peter Lenk Abstract Discrete-choice conjoint analysis is commonly used to measure subjects’ preference structures. Discrete-choice elicitation is often preferred to other measurement methods because it better aligns with actual choice behavior and avoids some of the welldocumented biases inherent to alternative methods, such as ratings. A limitation of discrete-choice is the loss of inter-subject comparability because the resulting utility structure is invariant to linear transformations. This deficit limits the application of discrete-choice conjoint to situations where only within-subject comparisons are meaningful, such as choice share simulation for product or service optimization. Discrete-choice conjoint enables one to order options for each subject, but one cannot sort subjects according to the intensity of their preferences. This paper proposes using auxiliary data to recover the origin and scale for discrete-choice conjoint to enable between-subject comparisons. The joint model moves the identification constraints from the discrete-choice to the rankings, thus recovering a common origin and scale. In two examples, we are able to sort subjects according the intensity of their preferences.