0
$\begingroup$

I require some assistance with HLM Conjoint Analysis.

Say a preference-survey asks multiple respondents which of three products they prefer, using different combinations of product features (each respondent answers multiple times with different product combinations each time). For example, a single choice may be do you prefer:

  • medium blue car priced at $20,000

  • small red car priced at $16,000

  • large yellow car priced at $19,000

How would I create utility / feature coefficients from such data? I am looking to create coefficients for each product feature (e.g. Car colour: blue, red, yellow) for every individual respondent using HLM. Is there a R package that is capable of this?

$\endgroup$
3
$\begingroup$

I think you're looking for the ChoiceModelR package. You specify a utility function, and the package will estimate coefficients, or part-worth utilities, using a hierarchical multinomial logit model.

$\endgroup$
0
$\begingroup$

For Bayesian choice modelling, I would strongly advise you to take a look at:
RSGHB package - Very flexible as you basically need to write your own utility functions
bayesm package (The book that goes with this package is a great introduction to HB: http://eu.wiley.com/WileyCDA/WileyTitle/productCd-0470863676.html)

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.