Have an idea?

Visit Sawtooth Software Feedback to share your ideas on how we can improve our products.

Is the term relative importance the technically correct term?

I submitted a paper on the results of my conjoint analysis and received a question or comment from two reviewers as to whether the term "relative importances" is the technically correct term?  I have already searched for it, but have not found any good information or alternative term.
Thank you very much!
asked Aug 1 by Pia (440 points)

1 Answer

0 votes
Well, the term isn't a technical term like you'd find in academic papers on conjoint analysis, but it IS the name of a type of derived importance analysis where importances are ratio scaled and sum to 100% (there's even a R package, Relaimpo that runs that kind of analysis).

I think it's safe to call conjoint importances "relative" because they only make sense relative to one another, and their absolute values don't really mean much.  However, I usually don't see conjoint importances used much in academic publishing - most of the emphasis there is on the utilities themselves.
answered Aug 1 by Keith Chrzan Platinum Sawtooth Software, Inc. (115,350 points)