Have an idea?

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

Significant difference of two (identical) studies

Dear all,

we conducted two studies on two clubs with the identical attributes and levels. Then we used latent class to identify different customer segments in both clubs. Both show kind of the same preference characteristics within the groups.
Is there any way to test for significant differences of their preferences/relative importance between those two studies. Unfortunately, there is no standard deviation of relative importance in LC, in order to conduct a t-test.

Thank you very much!
Mario
asked Oct 11 by Mario

1 Answer

0 votes
Mario,

You can, in the Lighthouse software select latent class analysis in the analysis menu then select settings and then "advanced" and request standard errors for the utilities (these are what you want to test, not differences in importances).
answered Oct 12 by Keith Chrzan Gold Sawtooth Software, Inc. (48,525 points)
...