Mlogit: how to intrepret model adequacy on fitstat

Question

Two questions regarding mlogit:

1. How exactly do you interpret goodness of fit using fitstat? Is it the R2? or the P-value of LR test?

2. Can the RRR be equated to an odds ratio

Answer 1

I assume you are using Stata even though it is missing from your tags. Here some comments:

1. I've never used fitstat. Regardless, the goodness of fit is treated as usual. You can take a look at the Wald/LR test of your model together with the pseudo-R2.

2. The RRR will be only equivalent to odds ratios if the multinomial logit is used when only two classes are available because it collapses into a logit specification. If it is not the case, the RRR need to be interpreted with respect to the baseline class (there is where the word relative, from relative-risk ratios (RRR) comes from).