I am using a mlogit command to analyse choice experiment that has 3 alternatives (1 of which is status-quo), and the attributes by which they vary is 4- 2 numeric variables and 2 categorical variable). My code shows the following error when using all the 4 variables. However when only numerical variables are used it gives significant results. Can someone please guide me on where I am going wrong. I can provide more details if needed.
resultsXLM <- mlogit(choice ~ renewable+bill+incentive+sourcing | 0, data=Datamodified,
rpar=c(renewable="n', bill='n', incentive='n', sourcing='n'), R=100, halton=NA, panel=TRUE)
result- Error in mlogit.start(formula = formula, data = data, mf = mf, start = start, :
unknown random parameter