I have question regarding the mnlogit package in R which I'll ask on StackOverflow as it's related to a specific language and library, however I won't be offended if someone decides to move it to Cross Validated (it was a hard choice of which StackExchange site was most appropriate).
I'm just trying to make sure I understand how this works, since the documentation isn't too detailed, I see some confusing/conflicting blog entries on this package, and because it's been a couple of years since I've dealt with choice models.
The example usage of mnlogit is basically as follows:
> require(mnlogit)
> data(Fish)
> head(Fish)
mode income alt price catch chid
1.beach FALSE 7083.332 beach 157.930 0.0678 1
1.boat FALSE 7083.332 boat 157.930 0.2601 1
1.charter TRUE 7083.332 charter 182.930 0.5391 1
1.pier FALSE 7083.332 pier 157.930 0.0503 1
2.beach FALSE 1250.000 beach 15.114 0.1049 2
2.boat FALSE 1250.000 boat 10.534 0.1574 2
> fm <- formula(mode ~ price | income | catch)
> result <- mnlogit(fm, Fish, "alt", ncores = 2)
What I find confusing is mode and alt. I would've thought that the dependent variable would be the multinomial choice, which appears to be alt (beach, boat, charter, or pier).
Instead it's this logical variable, mode. What's mode?
To try to clarify my understand I read an R-Bloggers article on the topic. It actually made things more confusing by repeating the Fish example, but with a preamble describing the dataset in this way:
A data frame containing :
mode - The choice set: beach, pier, boat, and charter price - price for a mode for an individual catch - fish catch rate for a mode for an individual income - monthly income of the individual decision-maker chid - decision maker ID
It describes mode as if it were alt then does not mention alt. Can someone explain this to me?
If mode really did take on the discrete choice values as described in the R-Bloggers article, then the model formula(mode ~ price | income | catch) would make sense to me... but mode is a logical variable, so I am thoroughly confused.