Discrete choice Analysis: What is the difference between consumer research and fit model function

Question

Hi, I am novice for this program. I am confused for a while about function to analyse Discrete choice modelling (Choice experiment)

1. Use Analyse>Consumer Research> Choice

2. Analyse > Fit Model (Nominal Logistic)

Both of them give me utility function and probablity but the result is not the same even if I used the same set of data

Result from Consumer Research> Choice

2. Fit Model (Nominal Logistic)

As you can see utility equation is not the same and "feature factor" is significant in first model but not significant in the ladder one.

In this case, What is the difference and which function should I use?

Sorry for a long post.

Thank you in advance.

NTN · Answer

Hi,

in JMP12 help under Choice Models - Fit Models for Choice Experiments there is a sentence: "The Choice Modeling platform uses a form of conditional logistic regression. Unlike simple logistic regression, choice modeling uses a linear model to model choices based on response attributes and not solely upon subject characteristics." Maybe this is an answer to your question.