Is there a standard name for a multinomial choice model where the observations are in the form of binary questions such as "do you prefer A to B" and "do you prefer B to D"? This seems like a common occurrence, and the likelihood is easy enough to write out by hand, but I'm having trouble searching for references.


Unless I misunderstood the question, this refers to paired preference (1) or pair comparison data. A well-known example of such a model is the Bradley-Terry model (2), which shares some connections with item scaling in psychometrics (3). There is an R package, BradleyTerry2, described in the JSS (2005) 12(1), Bradley-Terry Models in R, and a detailed overview in Agresti's CDA, pp. 436-439, with R code available in Laura Thompson's textbook, R (and S-PLUS) Manual to Accompany Agresti’s Categorical Data Analysis (2002) 2nd edition.


  1. Thurstone, L.L. (1927). A law of comparative judgment. Psychological Review, 3, 273-286.
  2. Bradley, R.A. and Terry, M.E. (1952). Rank analysis of incomplete block designs I: The methods of paired comparisons. Biometrika, 39, 324-345.
  3. Andrich, D. (1978). Relationships between the Thurstone and Rasch approaches to item scaling. Applied Psychological Measurement, 2(3), 451-462.

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.