I have conducted the pretest for a discrete choice experiment and try to compute the utility function for it using the mlogit package. I have converted the dataframe using:
TM2 <- mlogit.data(ride2, choice = "choice_actual_log", shape = "long",
chid.var = "respid_choice_mode", alt.var = "mode", drop.index = TRUE)
I attach a screenshot of the resulting dataframe.
When I now try to run the multinomial logit model, using the following code:
ml.TM <- mlogit(choice_actual_log ~ A1_1 +A1_2 +A1_3+A1_4, TM2, reflevel = "0")
I receive the following error message: "Error in solve.default(H, g[!fixed]) : Lapack routine dgesv: system is exactly singular: U[1,1] = 0"
Does anyone have an idea why this might be the case?
