cancel
Showing results for 
Show  only  | Search instead for 
Did you mean: 
Choose Language Hide Translation Bar
0 Kudos

Adding an MDS technique, called 'Multidimensional Unfolding'

I've been trying to use JMP's MDS program to provide a clearer visualization of values data I have. Working with your support team (particularly @PatrickGiuliano), it was suggested that I request this functionality -- hopefully for JMP 18.

 

'Multidimensional Unfolding', available in R, with the SMACOF package and maybe the best applied reference on it here: https://cran.r-project.org/web/packages/smacof/vignettes/smacof.pdf

Here's a brief summary related to the special Unfolding technique from Copilot: 

  1. Multidimensional Unfolding:

    • Unfolding is a related technique to MDS. It represents input preference data as distances in a low-dimensional space.
    • The smacof package has undergone major updates, including a complete re-implementation of multidimensional unfolding. Notable features include:
      • Monotone dissimilarity transformations: This allows for various unfolding scenarios, including row-conditional, circular, and external unfolding.
      • Optimal scaling of external variables: The constrained MDS implementation now extends to optimal scaling of external variables.

I'm including an article that provides the type of visualization I was looking for but cannot currently get through JMP 17 Pro. 

 

Thank you!