I am reading some materials about multidimensional unfolding and this concept "ideal points" are mentioned several times. I check these readings several times and could not find definition of this concept. The following are some screen captures of this concept

enter image description here enter image description here enter image description here

Based on my understanding, I am guessing the "ideal points" the row coordinates solved from the unfolding model if rows represent subjects and columns are objects of choice? Is my understanding right or wrong? Thank you.


Based on my knowledge of MDU, your understanding is correct. Supporting quote from Borg and Groenen(2005) page 293:

Individuals are represented as “ideal” points in the MDS space so that the distances from each ideal point to the object points correspond to the preference scores.

Therefore, when two or more individuals locate close to each other on the MDU configuration, their "taste" are similar. In other words, they have similar preference/ranking/row profile. Their "ideals" are the same.

  • $\begingroup$ Hello, I stumbled accross this topic and have become interested in it and am looking it up. Do you happen to know what the acronym "MDS" stands for in your quoted text? It's not multi-dimensional scaling, is it? $\endgroup$ – John Madden Jan 14 '16 at 21:01
  • $\begingroup$ Ah.. the book you cited is titled multi-dimensional scaling... disregard my retrospectively stupid question. $\endgroup$ – John Madden Jan 14 '16 at 21:03
  • $\begingroup$ Hi John, the book that I cited is almost the main book in the area as far as I know. It is very comprehensive. Unfolding is a variation of MDS, indeed the asymmetric matrix of unfolding can be transformed to symmetric matrix of MDS. I have worked with this technique in the last six months in order to use it in my PhD research. I may be able to help if you have more conceptual or technical questions. $\endgroup$ – Shahin Jan 14 '16 at 23:14
  • $\begingroup$ That's very kind of you, @Shahnin, I certainly will. Best of luck with your PhD, I hope to be in the same boat shortly. $\endgroup$ – John Madden Jan 14 '16 at 23:21

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.