Stack Overflow
Stack Overflow

Questions tagged [gmnl]

Questions related to the R package `gmnl`, which implements various types of Discrete Choice Models.

8 questions
3
votes
1 answer

Possible bug in R packages gmnl and Rchoice?

I want to estimate a binary random parameter logit in gmnl while accounting for unobserved and observed heterogeneity. When the Gender is a factor with 2 levels (0,1) it results at the error below. When Gender enters the gmnl function with the exact…
transmod_kdtk
  • 51
  • 6
2
votes
1 answer

Random Variable part in gmnl (R); Error: Random Variable are not in the data

Error Message in Random Parameter Part in gmnl code: "The following random variables are not in the data" I'm estimating a mixed MNL model, however, the gmnl keeps giving me the error message suggesting that the random part variable is NOT in the…
Zoe
  • 21
  • 1
1
vote
2 answers

How to Test the significance of difference in mean estimates in R?

Solved: I'm working on market research and want to conduct a Multinomial Logit Model by R based on the estimation below. It is designed to test whether consumers' exposure to specific advertisements could influence their preferences for the…
Sissie
  • 11
  • 2
1
vote
0 answers

`gmnl` unable to include Alternative Specific Constants (ASC) in Mixed-mixed MNL model

I am trying to estimate a Mixed-mixed multinomial logit model using the gmnl package. It works perfectly when not including Alternative Specific Constants (ASC), but it produces a weird error when incorporating them. The code below was taken (and…
Álvaro A. Gutiérrez-Vargas
  • 1,896
  • 2
  • 8
  • 24
1
vote
0 answers

gmnl Error 'no index for "choiceid" variable'

I have been able to make a mlogit.data object to input into the gmnl package for latent class analysis but I keep running into the problem where it says the choiced variable has no index. I saw there was another question about the same problem but…
Miha04
  • 23
  • 5
1
vote
1 answer

Modelling generic variables in a Latent class model with gmnl()

I have the problem in fomulating a model, where at least one variable is to be estimated independently from the classes, so one and the same coefficient for all classes. How could one do this? I am working with the R package…
maxatSOflow
  • 269
  • 3
  • 10
0
votes
0 answers

Estimate a latent class logit model in R? -varying' arguments must be the same length

I am trying to estimate a latent class logit model using panel data. I tried following this example: https://rpubs.com/msarrias1986/335556. I was told that the following code should work: RM <- mlogit.data(rm01, id.var = "ID", choice =…
Ping Guo
  • 1
  • 1
0
votes
0 answers

gmnl package, mixed logit 'mixl' Error: $ operator is invalid for atomic vectors

I am seeing this error is appearing with various other packages,for instance here, but the solutions do not seem to apply here. I am using the gmnl package and want to do a mixed logit, but run on the following error Error: $ operator is invalid for…
reggifanerosa
  • 3
  • 2