Cross Validated is a question and answer site for people interested in statistics, machine learning, data analysis, data mining, and data visualization. Join them; it only takes a minute:

Sign up
Here's how it works:
  1. Anybody can ask a question
  2. Anybody can answer
  3. The best answers are voted up and rise to the top

I am interested in utilizing Maximum Difference Scaling (Max Diff) for a survey, but apart from the Sawtooth software, I was not able to find a good answer on how to best analyze Max Diff. What is the best way to represent the result in my dataset, and which steps are used to analyze the data? I would prefer to use R or SPSS for analysis.

share|improve this question
please provide both example data and your desired outcome. otherwise explain why this post doesn't answer your question :) – Anthony Damico Jan 29 '13 at 17:38
"The most important thing that social psychologists have discovered over the last 50 years is that people are very unreliable informants about why they behaved as they did, made the judgment they did, or liked or disliked something." (Nisbett, R. E. [2007]. "Telling more than we can know." In Brockman, J., Ed., What is your dangerous idea? Today's leading thinkers on the unthinkable. New York: Harper, 269-271.) That statement can be applied to max-diff-based scores. Their value, in light of this, hardly justifies the difficulty one encounters in trying to compute them. – rolando2 Feb 4 '13 at 18:25
up vote 6 down vote accepted

Estimation of 'counts analysis' of Max-Diff data in both R and SPSS is straightforward (after recoding it is just computed as an average). This page explains the how to do such analyses.

More complicated analyses proceed by either using a 'tricked' logit model (e.g., Sawtooth Software), or, use the rank-ordered logit model (see Allison, P. D. and N. A. Christakis (1994). "Logit Models for Sets of Ranked Items." Sociological Methodology 24: 199-228), which is available in SAS (using PHREG with the EXACT option for ties) or in Q using a 'Question Type' of Ranking.

This page shows a case study which shows how to compute the counts, rank-ordered logit with ties and tricked logit models in R.

share|improve this answer

Your Answer


By posting your answer, you agree to the privacy policy and terms of service.

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