ApolloChoiceModelling forum

Dear Stephane and David,

I am estimating a fractional multinomial logit model using apollo. I notice that the standard t-ratios for most variables are quite low, while the robust t-ratios suggest that many of them are statistically significant.

I've never seen such a systematic discrepancy between ...

Hi Stephane,

I'm currently working on a paper where we estimated a multivariate ordered logit model with three dependent variables, using the mvord package instead of apollo. We are in the process of revising the paper for a journal, and one of the reviewers has requested confidence intervals for ...

Hi Stephane and David,

I'm trying to estimate a mixed ordered choice model with random threshold parameters. Bellow is the code I'm using to estimate the model. I got the following message: "Error in apollo_validate(op_settings, modelType, functionality, apollo_inputs) :
Tresholds for model ...

Hi Prof Stephane

Thanks for the answer. I'm using as reference the Chorus (2012) https://www.tandfonline.com/doi/abs/10.1080/01441647.2011.609947 and Dekker (2014) https://www.sciencedirect.com/science/article/abs/pii/S1755534514000360?via%3Dihub papers. I'm aware of the differences between the RUM ...

Hi David and Stephane,

I have a question about the VTT error calculated from a RRM model. If I understood correctly the paper of Daly et al. (2012) about the computation of this measure, we calculate errors from a transformation of the parameters, and in the case of VTT is the ratio of the ...

I found the error prof Hess, I was specifying in a wrong way the SEX variable and now it works. Thanks!

Best,
Gabriel

My model has an ordered variable with 4 outcomes, I just put two variables to test with it works, but then I get the following message:

Error in apollo_validate(ol_settings, modelType, functionality, apollo_inputs) :
Some values inside V are not finite for model component "model"
Além disso ...

Hi prof Hess,

I think it's a silly question, but, if I want to specify an ordered model like in the polr function from the MASS package, where I specify the utility (in the Manual says V is a numeric vector) in the model? All the examples in the manual and the topics here discuss the specification ...

Hi David,

I have a question about computing Average Marginal effect for dummy variables, when you write P(i | x1=1) - P(i | x1=0), does it mean that I need to compute the probability for the complete estimated sample, and then subselect in the sample the observations with x1=1 and x1=0 and ...

Thanks prof Hess!

Best regards,

Gabriel