Once I have an estimated or calibrated multinomial logit and glmer models, I need to see how the model is strong in its prediction capabilities by observing and checking the whole capacity of calibrated model.

Example: use the provided code with provided data for more discussion.

The calibrated model looks like,

library(mlogit)

library(foreign)

library(MASS)

library(lme4)

library(lattice)

mydata