Have an idea?

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

Estimating CBC model with mlogit in R - problem with none parameter

I would like to estimate CBC part-worth utilities with the mlogit package in R. I transferred the raw data from Lighthouse Studio to R.
 
My CBC design includes a none option as fourth option. It seems that mlogit has a problem with this none option producing the error message “Error in if (abs(x - oldx) < ftol) { : missing value where TRUE/FALSE needed”. I guess that mlogit cannot deal with zeros as covariates (and choices). At least, if I just delete the none option lines per choice task it does not fix the problem (as then I have zeros for the choices), only if I delete the none option line AND manually just randomly select one of the remaining three alternatives per choice task.
 
Does anyone have an advice on how to deal with this problem with mlogit in R - or more general - on how to analyze CBC data with none options in R?
 
Many thanks in advance for your help.
asked Apr 6 by nina (120 points)

Your solution to the original question

Please only use this to answer the original question. Otherwise please use comments.
Your name to display (optional):
Privacy: Your email address will only be used for sending these notifications.
Anti-spam verification:

To avoid this verification in future, please log in or register.
...