Simulation with Conjoint Analysis

#1
Hi everyone,

With SPSS when I run a simulation with conjoint analysis I got this message:

"142 out of 155 subjects are used in the Bradley-Terry-Luce and Logit methods because these subjects have all nonnegative scores".

I think SPSS excluded those respondents because their simulated score was negative for some profiles.

Each excluded respondent displays this message:
"Negative simulation scores or all zero simulation scores are found. This subject will not be included in computing preference probabilities using the Bradley-Terry-Luce or Logit methods"

Is there a way to include the excluded subject?
Is it possible to avoid this issue with other softwares?

Thank you very much,

Fabio Spinnato
 
#2
Hi,

It would be helpful if you describe the data you're using. Are we talking about raw or zero-centered utility scores? It is quite normal to end up with negative utility for a specific concept you're measuring, so I'm not clear as to why you're getting this error.

I use Sawtooth software for conjoint, so I'm not familiar with how SPSS runs conjoint analysis.